CN113486882A - Image recognition method and device based on user behaviors, electronic equipment and medium - Google Patents
Image recognition method and device based on user behaviors, electronic equipment and medium Download PDFInfo
- Publication number
- CN113486882A CN113486882A CN202111046516.6A CN202111046516A CN113486882A CN 113486882 A CN113486882 A CN 113486882A CN 202111046516 A CN202111046516 A CN 202111046516A CN 113486882 A CN113486882 A CN 113486882A
- Authority
- CN
- China
- Prior art keywords
- corpus
- image
- information
- score
- preset
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- 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)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the disclosure discloses an image recognition method, an image recognition device, electronic equipment and a medium based on user behaviors. One embodiment of the method comprises: acquiring the corpus information of a corresponding article submitted by a user; inputting the corpus fields included in the corpus information into a pre-trained corpus scoring model to obtain corpus scores corresponding to the corpus fields; responding to the fact that the corpus score is larger than or equal to the preset corpus score, inputting the object image into a pre-trained image recognition model, and obtaining an image recognition result; in response to the fact that the object represented by the image recognition result is consistent with the object represented by the corpus field, inputting the object image into a pre-trained image scoring model to obtain an image score of the corresponding object image; and responding to the image score being more than or equal to the preset image score, and adding the corpus information into a preset target corpus information group. This embodiment ensures that the displayed picture and text are consistent.
Description
Technical Field
Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to an image recognition method and apparatus based on user behavior, an electronic device, and a medium.
Background
In order to increase the logistics transportation amount of the logistics platform for the goods approved by people, the logistics platform generally screens out the positive comments (e.g., approved comments) of the goods submitted by the users, and places or intensively displays the positive comments on the display interface of the logistics platform. Here, the comment may be corpus information. Currently, positive comments are screened in a generally adopted manner as follows: by manually identifying positive comments submitted by the user.
However, when the above-described manner is adopted, there are generally the following technical problems:
firstly, manual identification is usually identification of character comments, and whether pictures and characters in the comments correspond to each other or not is not considered, so that the problem of obvious image-text inconsistency is caused;
secondly, it is difficult to reasonably sort the displayed positive comments, and the positive comments of the articles are not effectively displayed, which may affect the conveying amount of the articles corresponding to the positive comments. .
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 image recognition methods, apparatuses, electronic devices, and computer-readable media based on user behavior 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 an image recognition method based on user behavior, the method including: obtaining the corpus information of a corresponding article submitted by a user, wherein the corpus information comprises a corpus field and an article image; inputting the corpus fields included in the corpus information into a pre-trained corpus scoring model to obtain corpus scores corresponding to the corpus fields; responding to the fact that the corpus score is larger than or equal to a preset corpus score, and inputting the article image into a pre-trained image recognition model to obtain an image recognition result; in response to the object represented by the image recognition result being consistent with the object represented by the corpus field, inputting the object image into a pre-trained image scoring model to obtain an image score corresponding to the object image; and responding to the image score being more than or equal to a preset image score, and adding the corpus information into a preset target corpus information group.
In a second aspect, some embodiments of the present disclosure provide an image recognition apparatus based on user behavior, the apparatus including: the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire the corpus information of a corresponding article submitted by a user, and the corpus information comprises a corpus field and an article image; a first input unit configured to input a corpus field included in the corpus information into a pre-trained corpus scoring model, so as to obtain a corpus score corresponding to the corpus field; the second input unit is configured to respond to the fact that the corpus score is larger than or equal to a preset corpus score, and input the article image into a pre-trained image recognition model to obtain an image recognition result; a third input unit, configured to input the item image into a pre-trained image scoring model in response to that the item represented by the image recognition result is consistent with the item represented by the corpus field, so as to obtain an image score corresponding to the item image; and the adding unit is configured to add the corpus information to a preset target corpus information group in response to the image score being greater than or equal to a preset image score.
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: by the image identification method based on the user behaviors, displayed pictures can be ensured to correspond to characters. The reason for the obvious image-text inconsistency is that: the manual identification is usually the identification of text comments, and whether pictures and texts in the comments correspond to each other or not is not considered, so that the problem of obvious picture-text inconsistency is caused. Based on this, the image recognition method based on user behavior according to some embodiments of the present disclosure first obtains the corpus information of the corresponding item submitted by the user. The corpus information includes corpus fields and object images. Therefore, data support is provided for subsequently determining whether the corpus information submitted by the user is high-quality comments. And secondly, inputting the corpus fields included in the corpus information into a pre-trained corpus scoring model to obtain corpus scores corresponding to the corpus fields. Therefore, data support is provided for preliminarily judging whether the corpus information is high-quality comments or not. And then, responding to the fact that the corpus score is larger than or equal to a preset corpus score, inputting the article image into a pre-trained image recognition model, and obtaining an image recognition result. Thus, it may be convenient to determine whether a corpus field in the corpus information corresponds to an item image. Then, in response to the fact that the object represented by the image recognition result is consistent with the object represented by the corpus field, the object image is input into a pre-trained image scoring model, and an image score corresponding to the object image is obtained. Therefore, data support is provided for further determining whether the corpus information is good comments. And finally, responding to the image score being more than or equal to a preset image score, and adding the corpus information into a preset target corpus information group. Therefore, whether the language material field submitted by the user is consistent with the article image can be determined through the recognition of the language material field and the article image in the language material information. Therefore, the displayed pictures and characters are ensured to be corresponding.
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 user behavior based image recognition method according to some embodiments of the present disclosure;
FIG. 2 is a flow diagram of some embodiments of a user behavior based image recognition method according to the present disclosure;
FIG. 3 is a flow diagram of further embodiments of image recognition methods based on user behavior according to the present disclosure;
FIG. 4 is a schematic block diagram of some embodiments of an image recognition apparatus based on user behavior according to the present disclosure;
FIG. 5 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 an image recognition method based on user behavior according to some embodiments of the present disclosure.
In the application scenario of fig. 1, first, the computing device 101 may obtain corpus information 102 of a corresponding item submitted by a user. The corpus information 102 includes a corpus field 1021 and an item image 1022. Next, the computing device 101 may input the corpus field 1021 included in the corpus information 102 into a pre-trained corpus scoring model 103, so as to obtain a corpus score 104 corresponding to the corpus field 1021. Then, the computing device 101 may input the item image 1022 into a pre-trained image recognition model 105 to obtain an image recognition result 106 in response to the corpus score 104 being greater than or equal to a preset corpus score. Then, in response to that the item represented by the image recognition result 106 is consistent with the item represented by the corpus field 1021, the computing device 101 may input the item image 1022 into a pre-trained image scoring model 107, so as to obtain an image score 108 corresponding to the item image 1022. Finally, the computing device 101 may add the corpus information 102 to a preset target corpus information set in response to the image score 1022 being greater than or equal to a preset image score.
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 200 of some embodiments of a user behavior based image recognition method in accordance with the present disclosure is shown. The image recognition method based on the user behaviors comprises the following steps:
In some embodiments, an executing subject (e.g., the computing device 101 shown in fig. 1) of the image recognition method based on user behavior may acquire the corpus information of the corresponding item submitted by the user from the terminal device by means of wired connection or wireless connection. The corpus information includes corpus fields and object images. Here, the corpus information may refer to feedback information (comment) submitted by the user on the acquired (purchased) item. Here, the corpus field may refer to text feedback information submitted by the user for the acquired item. Here, the item image may represent image feedback information (which may be png format pictures) submitted by the user for the acquired item. As an example, the corpus information may be "XX items very well used, XX.
In some embodiments, the execution body may input the corpus fields included in the corpus information into a pre-trained corpus scoring model to obtain corpus scores corresponding to the corpus fields. Here, the corpus scoring model may be a neural network model in which a corpus field is input data and a score for the corpus field is output data. For example, the corpus scoring model may be an open model Senta or a text classification model TextRCNN. For example, inputting the corpus field "XX item is very good" into the pre-trained corpus scoring model, the corpus score "8 points" corresponding to the corpus field can be obtained.
In some embodiments, the executing body may input the article image into a pre-trained image recognition model in response to the corpus score being greater than or equal to a preset corpus score, so as to obtain an image recognition result. Here, the setting of the preset corpus score is not limited. For example, the preset corpus score may be 7.5 points. Here, the image recognition model may be a neural network model in which an article image is input data and an article name corresponding to the article image is output data. For example, the image recognition model may be a Deep residual network (ResNet) or an EfficientNet neural network model. For example, the article image "xx.png" may be input into a pre-trained image recognition model, resulting in an image recognition result "XX article".
In some embodiments, the executing agent may input the item image into a pre-trained image scoring model in response to that the item represented by the image recognition result is consistent with the item represented by the corpus field, so as to obtain an image score corresponding to the item image. Here, the image scoring model may be a neural network model in which an item image is input data and a score of the item image is output data. For example, the Image scoring model may be a NIMA model (Neural Image Assessment). For example, in response to the fact that the item "XX" represented by the image recognition result is consistent with the item "XX" represented by the corpus field, the item image "xx.png" may be input into a pre-trained image scoring model, so as to obtain an image score "9" corresponding to the item image.
In some embodiments, the execution subject may add the corpus information to a preset target corpus information set in response to the image score being greater than or equal to a preset image score. Here, the preset target corpus information group may be a target corpus information group composed of corpus information items including a corpus field score equal to or greater than a preset corpus score, an item image score equal to or greater than a preset image score, and an item represented by the corpus field and an item represented by the item image that are consistent with each other. Here, the setting of the preset image score is not limited. For example, the preset image score may be 8 points.
Optionally, in response to the corpus score being smaller than the preset corpus score, corpus feedback information corresponding to the corpus information is received.
In some embodiments, the execution body may receive corpus feedback information corresponding to the corpus information in response to the corpus score being less than the predetermined corpus score. In practice, the execution main body may receive the corpus feedback information (reply information) corresponding to the corpus information submitted by the staff.
Optionally, the corpus feedback information is sent to the user side of the user for display.
In some embodiments, the execution main body may send the corpus feedback information to the user side of the user for display. Here, the user terminal may be a mobile phone terminal of the user.
Optionally, in response to not receiving the corpus reply information corresponding to the corpus feedback information sent by the user end within a first preset duration, adding the corpus information to a preset abnormal corpus information group.
In some embodiments, the execution main body may add the corpus information to a preset abnormal corpus information group in response to not receiving the corpus reply information corresponding to the corpus feedback information sent by the user end within a first preset duration. Here, the abnormal corpus information in the abnormal corpus information group is the corpus information that includes a corpus score smaller than the preset corpus score and does not receive the corpus reply information sent by the user side. Here, the abnormal corpus information group may be displayed at the end of an interface for displaying corpus information at the user side. Here, the setting of the first preset time period is not limited. Here, the corpus reply message may refer to a text reply message.
Optionally, in response to receiving a corpus reply message corresponding to the corpus feedback message sent by the user end within the first preset time period, the corpus reply message is input into the corpus scoring model, so as to obtain a corpus reply score corresponding to the corpus reply message.
In some embodiments, the execution main body may input the corpus reply information into the corpus scoring model in response to receiving the corpus reply information corresponding to the corpus feedback information sent by the user end within the first predetermined time period, so as to obtain a corpus reply score corresponding to the corpus reply information.
Optionally, in response to the corpus reply score being greater than or equal to a preset corpus reply score, the corpus information, the corpus feedback information, and the corpus reply information are combined to generate first corpus display information.
In some embodiments, the execution main body may combine the corpus information, the corpus feedback information, and the corpus reply information to generate a first corpus display information in response to the corpus reply score being greater than or equal to a predetermined corpus reply score. Here, the combining process may be a splicing process.
Optionally, the first corpus display information is sent to a preset display terminal for displaying.
In some embodiments, the execution main body may send the first corpus display information to a preset display terminal for displaying. Here, the preset display terminal may be a mobile phone terminal of any user submitting the corpus information.
The above embodiments of the present disclosure have the following advantages: by the image identification method based on the user behaviors, displayed pictures can be ensured to correspond to characters. The reason for the obvious image-text inconsistency is that: the manual identification is usually the identification of text comments, and whether pictures and texts in the comments correspond to each other or not is not considered, so that the problem of obvious picture-text inconsistency is caused. Based on this, the image recognition method based on user behavior according to some embodiments of the present disclosure first obtains the corpus information of the corresponding item submitted by the user. The corpus information includes corpus fields and object images. Therefore, data support is provided for subsequently determining whether the corpus information submitted by the user is high-quality comments. And secondly, inputting the corpus fields included in the corpus information into a pre-trained corpus scoring model to obtain corpus scores corresponding to the corpus fields. Therefore, data support is provided for preliminarily judging whether the corpus information is high-quality comments or not. And then, responding to the fact that the corpus score is larger than or equal to a preset corpus score, inputting the article image into a pre-trained image recognition model, and obtaining an image recognition result. Thus, it may be convenient to determine whether a corpus field in the corpus information corresponds to an item image. Then, in response to the fact that the object represented by the image recognition result is consistent with the object represented by the corpus field, the object image is input into a pre-trained image scoring model, and an image score corresponding to the object image is obtained. Therefore, data support is provided for further determining whether the corpus information is good comments. And finally, responding to the image score being more than or equal to a preset image score, and adding the corpus information into a preset target corpus information group. Therefore, whether the language material field submitted by the user is consistent with the article image can be determined through the recognition of the language material field and the article image in the language material information. Therefore, the displayed pictures are consistent with the displayed characters.
With further reference to FIG. 3, a flow 300 of further embodiments of a user behavior based image recognition method according to the present disclosure is shown. The image recognition method based on the user behaviors comprises the following steps:
In some embodiments, the specific implementation manner and technical effects of steps 301 and 305 may refer to steps 201 and 205 in those embodiments corresponding to fig. 2, which are not described herein again.
In some embodiments, an executing subject of the user behavior-based image recognition method (e.g., the computing device 101 shown in fig. 1) may receive image feedback information corresponding to the item image in response to the image score being less than the preset image score. In practice, the execution subject may receive image feedback information (reply information) corresponding to the article image submitted by a worker.
In some embodiments, the execution subject may send the image feedback information to a user side of the user for display.
In some embodiments, the execution main body may add the corpus information to a preset abnormal corpus information group in response to not receiving an image reply message corresponding to the image feedback information sent by the user end within a second preset duration. Here, the abnormal corpus information in the abnormal corpus information group is the corpus information that includes a corpus score smaller than the preset corpus score and does not receive the corpus reply information sent by the user side. Here, the abnormal corpus information group may be displayed at the end of an interface for displaying corpus information at the user side. Here, the setting of the second preset time period is not limited. Here, the image reply information may be a text reply information.
In some embodiments, according to each corpus score and each image score corresponding to the target corpus information set, the executing entity may perform a sorting process on the target corpus information set by the following steps to generate a target corpus information sequence:
step one, determining the sum of the linguistic data score and the image score corresponding to each target linguistic data information in the target linguistic data information group as a linguistic data score value to obtain a linguistic data score value group;
and secondly, sequencing the target corpus information group according to the fact that the corpus score values in the corpus score value group are from large to small so as to generate a target corpus information sequence.
In some embodiments, according to the corpus score and the image score corresponding to the abnormal corpus information set, the execution main body may perform a sorting process on the abnormal corpus information set by the following steps to generate an abnormal corpus information sequence:
the method comprises the following steps that firstly, according to the fact that the corpus scores corresponding to the abnormal corpus information groups are from large to small, the abnormal corpus information groups are sorted, and a first abnormal corpus information sequence is generated.
And secondly, for each first abnormal corpus information with the same corpus score in the first abnormal corpus information sequence, sequencing each first abnormal corpus information with the same corpus score in the first abnormal corpus information sequence according to the image score corresponding to each first abnormal corpus information from large to small so as to generate an abnormal corpus information sequence. In practice, for each first abnormal corpus information with the same corpus score in the first abnormal corpus information sequence, each first abnormal corpus information with the same corpus score in the first abnormal corpus information sequence is sorted according to the descending order of each image score corresponding to each first abnormal corpus information with the same corpus score to generate an abnormal corpus information sequence.
And 311, splicing the target corpus information sequence and the abnormal corpus information sequence to generate a corpus information sequence to be displayed.
In some embodiments, the execution main body may perform a splicing process on the target corpus information sequence and the abnormal corpus information sequence to generate a corpus information sequence to be displayed. Here, the abnormal corpus information sequence may be spliced after the target corpus information sequence.
And step 312, sending the corpus information sequence to be displayed to a preset display terminal for displaying.
In some embodiments, the execution main body may send the corpus information sequence to be displayed to a preset display terminal for displaying. Here, the preset display terminal may be a mobile phone terminal of any user submitting the corpus information.
Optionally, in response to receiving, within the second preset time period, image reply information corresponding to the image feedback information sent by the user terminal, the image reply information is input to the language score model, so as to obtain an image reply score corresponding to the image reply information.
In some embodiments, the execution main body may input the image reply information into the language score model in response to receiving the image reply information corresponding to the image feedback information sent by the user end within the second preset time period, so as to obtain an image reply score corresponding to the image reply information.
Optionally, in response to that the image reply score is greater than or equal to a preset image reply score, the corpus information, the image feedback information, and the image reply information are combined to generate second corpus display information.
In some embodiments, the execution body may combine the corpus information, the image feedback information, and the image reply information to generate a second corpus presentation information in response to the image reply score being greater than or equal to a preset image reply score. Here, the combining process may refer to a splicing process.
Optionally, the second corpus display information is sent to a preset display terminal for displaying.
In some embodiments, the execution main body may send the second corpus display information to a preset display terminal for displaying. Here, the preset display terminal may be a mobile phone terminal of any user submitting the corpus information.
The related content in step 309 and 311 serves as an invention point of the disclosure, and the technical problem that the second technical problem mentioned in the background art is that the displayed positive comments are difficult to be reasonably sorted, and the positive comments of the articles are not effectively displayed, which may affect the conveying amount of the articles corresponding to the positive comments is solved. Factors that affect the conveyance amount of the article corresponding to the positive comment are often as follows: the displayed positive comments are difficult to reasonably sort, and the positive comments of the articles are not effectively displayed, so that the conveying amount of the articles corresponding to the positive comments is influenced. If the above-mentioned factors are solved, the effect of improving the conveying amount of the article corresponding to the positive comment can be achieved. In order to achieve this effect, the present disclosure first performs a sorting process on the target corpus information set according to the corpus score and the image score corresponding to the target corpus information set, so as to generate a target corpus information sequence. Therefore, the target corpus information group can be comprehensively sequenced according to the corpus scores and the image scores corresponding to the target corpus information group. And then, according to each corpus score and image score corresponding to the abnormal corpus information group, sequencing the abnormal corpus information group to generate an abnormal corpus information sequence. Therefore, the abnormal corpus information groups can be sorted according to the corpus scores and the image scores corresponding to the abnormal corpus information groups. And finally, splicing the target corpus information sequence and the abnormal corpus information sequence to generate a corpus information sequence to be displayed. Therefore, the displayed front comments can be reasonably sorted, and the front comments of the articles can be effectively displayed to the user. Therefore, the user flow of the fresh platform is improved, and the article conveying capacity of the fresh platform is improved. And further the logistics transportation amount of the logistics platform is improved.
As can be seen from fig. 3, compared with the description of some embodiments corresponding to fig. 2, the flow 300 of the image recognition method based on user behavior in some embodiments corresponding to fig. 3 completes reasonable ranking of the presented positive comments, and the positive comments of the item can be effectively presented to the user. Therefore, the user flow of the fresh platform is improved, and the article conveying capacity of the fresh platform is improved. And further the logistics transportation amount of the logistics platform is improved.
With further reference to fig. 4, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an image recognition apparatus based on user behavior, which correspond to those of the method embodiments described above in fig. 2, and which may be applied in various electronic devices in particular.
As shown in fig. 4, the image recognition apparatus 500 based on user behavior of some embodiments includes: an acquisition unit 401, a first input unit 402, a second input unit 403, a third input unit 404, and an addition unit 405. The obtaining unit 401 is configured to obtain corpus information of a corresponding article submitted by a user, where the corpus information includes a corpus field and an article image; the first input unit 402 is configured to input the corpus fields included in the corpus information into a pre-trained corpus scoring model, so as to obtain corpus scores corresponding to the corpus fields; the second input unit 403 is configured to input the item image into a pre-trained image recognition model in response to the corpus score being greater than or equal to a preset corpus score, so as to obtain an image recognition result; the third input unit 404 is configured to input the item image into a pre-trained image scoring model in response to that the item represented by the image recognition result is consistent with the item represented by the corpus field, so as to obtain an image score corresponding to the item image; the adding unit 405 is configured to add the corpus information to a preset target corpus information group in response to the image score being greater than or equal to a preset image score.
It will be understood that the elements described in the apparatus 400 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.
Referring now to FIG. 5, a block diagram of an electronic device (e.g., computing device 101 of FIG. 1) 500 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 5 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. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 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. 5 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 via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, 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 above 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 apparatus; 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: obtaining the corpus information of a corresponding article submitted by a user, wherein the corpus information comprises a corpus field and an article image; inputting the corpus fields included in the corpus information into a pre-trained corpus scoring model to obtain corpus scores corresponding to the corpus fields; responding to the fact that the corpus score is larger than or equal to a preset corpus score, and inputting the article image into a pre-trained image recognition model to obtain an image recognition result; in response to the object represented by the image recognition result being consistent with the object represented by the corpus field, inputting the object image into a pre-trained image scoring model to obtain an image score corresponding to the object image; and responding to the image score being more than or equal to a preset image score, and adding the corpus information into a preset target corpus information group.
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 an acquisition unit, a first input unit, a second input unit, a third input unit, and an addition unit. The names of the units do not form a limitation on the units themselves in some cases, and for example, the adding unit may be further described as a unit that adds the corpus information to a preset target corpus information group in response to the image score being equal to or greater than a preset image score.
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 (10)
1. An image recognition method based on user behavior comprises the following steps:
obtaining the corpus information of a corresponding article submitted by a user, wherein the corpus information comprises a corpus field and an article image;
inputting the corpus fields included in the corpus information into a pre-trained corpus scoring model to obtain corpus scores corresponding to the corpus fields;
responding to the fact that the corpus score is larger than or equal to a preset corpus score, and inputting the article image into a pre-trained image recognition model to obtain an image recognition result;
in response to the fact that the object represented by the image recognition result is consistent with the object represented by the corpus field, inputting the object image into a pre-trained image scoring model to obtain an image score corresponding to the object image;
and responding to the image score being more than or equal to a preset image score, and adding the corpus information into a preset target corpus information group.
2. The method of claim 1, wherein the method further comprises:
responding to the corpus score smaller than the preset corpus score, and receiving corpus feedback information corresponding to the corpus information;
sending the corpus feedback information to a user side of the user for display;
and in response to that the corpus reply information which is sent by the user side and corresponds to the corpus feedback information is not received within a first preset time length, adding the corpus information to a preset abnormal corpus information group.
3. The method of claim 1, wherein the method further comprises:
receiving image feedback information corresponding to the item image in response to the image score being less than the preset image score;
sending the image feedback information to a user side of the user for displaying;
and in response to that the image reply information which is sent by the user side and corresponds to the image feedback information is not received within a second preset time length, adding the corpus information to a preset abnormal corpus information group.
4. The method of claim 2 or 3, wherein the method further comprises:
according to each corpus score and image score corresponding to the target corpus information group, sequencing the target corpus information group to generate a target corpus information sequence;
sorting the abnormal corpus information group according to each corpus score and image score corresponding to the abnormal corpus information group to generate an abnormal corpus information sequence;
splicing the target corpus information sequence and the abnormal corpus information sequence to generate a corpus information sequence to be displayed;
and sending the corpus information sequence to be displayed to a preset display terminal for displaying.
5. The method according to claim 4, wherein the sorting the target corpus information group according to the corpus score and the image score corresponding to the target corpus information group to generate a target corpus information sequence comprises:
determining the sum of the corpus score and the image score corresponding to each target corpus information in the target corpus information group as a corpus score value to obtain a corpus score value group;
and sequencing the target corpus information group according to the fact that the corpus score values in the corpus score value group are from large to small so as to generate a target corpus information sequence.
6. The method according to claim 4, wherein the sorting the abnormal corpus information group according to the corpus score and the image score corresponding to the abnormal corpus information group to generate an abnormal corpus information sequence comprises:
sorting the abnormal corpus information group according to the fact that the score of each corpus corresponding to the abnormal corpus information group is from large to small so as to generate a first abnormal corpus information sequence;
and for each piece of first abnormal corpus information with the same corpus score in the first abnormal corpus information sequence, sequencing each piece of first abnormal corpus information with the same corpus score in the first abnormal corpus information sequence according to the fact that each image score corresponding to each piece of first abnormal corpus information is from large to small so as to generate an abnormal corpus information sequence.
7. The method of claim 3, wherein the method further comprises:
in response to receiving image reply information corresponding to the image feedback information sent by the user side within the second preset time, inputting the image reply information into the corpus scoring model to obtain an image reply score corresponding to the image reply information;
responding to the image reply score being larger than or equal to a preset image reply score, and combining the corpus information, the image feedback information and the image reply information to generate second corpus display information;
and sending the second corpus display information to a preset display terminal for displaying.
8. An image recognition apparatus based on user behavior, comprising:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is configured to acquire the corpus information of a corresponding article submitted by a user, and the corpus information comprises a corpus field and an article image;
the first input unit is configured to input the corpus fields included in the corpus information into a pre-trained corpus scoring model to obtain corpus scores corresponding to the corpus fields;
the second input unit is configured to respond to the fact that the corpus score is larger than or equal to a preset corpus score, and input the article image into a pre-trained image recognition model to obtain an image recognition result;
a third input unit, configured to input the item image into a pre-trained image scoring model in response to that the item represented by the image recognition result is consistent with the item represented by the corpus field, so as to obtain an image score corresponding to the item image;
an adding unit configured to add the corpus information to a preset target corpus information group in response to the image score being greater than or equal to a preset image score.
9. 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 1-7.
10. 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 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111046516.6A CN113486882A (en) | 2021-09-08 | 2021-09-08 | Image recognition method and device based on user behaviors, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111046516.6A CN113486882A (en) | 2021-09-08 | 2021-09-08 | Image recognition method and device based on user behaviors, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113486882A true CN113486882A (en) | 2021-10-08 |
Family
ID=77947340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111046516.6A Pending CN113486882A (en) | 2021-09-08 | 2021-09-08 | Image recognition method and device based on user behaviors, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113486882A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423356A (en) * | 2017-05-31 | 2017-12-01 | 北京京东尚科信息技术有限公司 | The processing method and processing device of evaluation information, computer-readable medium, electronic equipment |
| CN110097419A (en) * | 2019-03-29 | 2019-08-06 | 努比亚技术有限公司 | Commodity data processing method, computer equipment and storage medium |
| CN112445908A (en) * | 2019-08-29 | 2021-03-05 | 北京京东尚科信息技术有限公司 | Commodity comment information display method and device, electronic equipment and storage medium |
-
2021
- 2021-09-08 CN CN202111046516.6A patent/CN113486882A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423356A (en) * | 2017-05-31 | 2017-12-01 | 北京京东尚科信息技术有限公司 | The processing method and processing device of evaluation information, computer-readable medium, electronic equipment |
| CN110097419A (en) * | 2019-03-29 | 2019-08-06 | 努比亚技术有限公司 | Commodity data processing method, computer equipment and storage medium |
| CN112445908A (en) * | 2019-08-29 | 2021-03-05 | 北京京东尚科信息技术有限公司 | Commodity comment information display method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107665225B (en) | Information pushing method and device | |
| US11412070B2 (en) | Method and apparatus for generating information | |
| CN107295095A (en) | The method and apparatus for pushing and showing advertisement | |
| CN112311841A (en) | Information pushing method and device, electronic equipment and computer readable medium | |
| CN112819512B (en) | Text processing method, device, equipment and medium | |
| CN111274490A (en) | Method and device for processing consultation information | |
| CN111209432A (en) | Information acquisition method and device, electronic equipment and computer readable medium | |
| CN114297278A (en) | Method, system and device for quickly writing batch data | |
| CN107885872B (en) | Method and device for generating information | |
| CN111262778B (en) | Invitation link information processing method and device, electronic equipment and readable medium | |
| CN109947526B (en) | Method and apparatus for outputting information | |
| CN111078636A (en) | Marketing data processing method and system and related equipment | |
| CN116109374A (en) | Resource bit display method, device, electronic equipment and computer readable medium | |
| CN116245595A (en) | Method, apparatus, electronic device and computer readable medium for transporting supply end article | |
| CN113486882A (en) | Image recognition method and device based on user behaviors, electronic equipment and medium | |
| CN112860999B (en) | Information recommendation method, device, equipment and storage medium | |
| CN115671723A (en) | Resource processing method, device, equipment and medium | |
| CN111143740B (en) | Information processing method and device and electronic equipment | |
| CN112348612B (en) | Order generation method and device | |
| CN111125501B (en) | Method and device for processing information | |
| CN111953502A (en) | Information announcement method and device and electronic equipment | |
| CN113609413A (en) | Questionnaire delivery method, system, equipment, medium and product | |
| CN112507385A (en) | Information display method and device and electronic equipment | |
| CN112214695A (en) | Information processing method and device and electronic equipment | |
| CN113177174B (en) | Feature construction method, content display method and related device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211008 |