CN111177521A - Method and device for determining query term classification model - Google Patents
Method and device for determining query term classification model Download PDFInfo
- Publication number
- CN111177521A CN111177521A CN201811243106.9A CN201811243106A CN111177521A CN 111177521 A CN111177521 A CN 111177521A CN 201811243106 A CN201811243106 A CN 201811243106A CN 111177521 A CN111177521 A CN 111177521A
- Authority
- CN
- China
- Prior art keywords
- type
- query
- image
- classification model
- 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
- 238000013145 classification model Methods 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000002372 labelling Methods 0.000 abstract description 5
- 230000035945 sensitivity Effects 0.000 description 28
- 238000004891 communication Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 230000009193 crawling Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 208000001613 Gambling Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a method and a device for determining a query term classification model, wherein images in historical query results are identified through the image classification model, and if one historical query result comprises an image of a target type, the type of a historical query term corresponding to the historical query result is determined to be the target type. The recognized historical query words of the target type can be used for training a query word classification model, so that the query word classification model can realize the function of recognizing whether the type of the query words is the target type. When the type of the query word needs to be determined to be the target type, manual labeling is not needed, and the method can be realized directly through the query word classification model, so that the identification efficiency of the type of the query word is improved.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a method and an apparatus for determining a query term classification model.
Background
The user inputs the query term through the search engine, and the query result related to the query term can be obtained.
If the search engine can determine the type of the query term or the query intention corresponding to the query term, the search can be performed in a targeted manner based on the type of the query term, so that the search efficiency and the search accuracy are improved. At present, the type of the query word is mainly identified by manually identifying and labeling the query word with a manually identified type label.
The method has low efficiency, is far from keeping up with the updating speed of the query words used by the user, and is difficult to adapt to the current network searching requirement.
Disclosure of Invention
In order to solve the technical problem, the application provides a method and a device for determining a query term classification model, which can be directly realized through the query term classification model, so that the identification efficiency of the query term type is improved.
The embodiment of the application discloses the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for determining a query term classification model, where the method includes:
identifying whether the historical query result corresponding to the historical query word comprises an image of a target type or not according to the image classification model;
determining a historical query word corresponding to a historical query result comprising the image of the target type as the historical query word of the target type;
and training a query term classification model according to the historical query terms of the target type, wherein the query term classification model is used for identifying whether the type of the query term is the target type.
Optionally, the method further includes:
acquiring an image set of the target type;
and training the image classification model according to the image set, wherein the image classification model is used for identifying whether the type of the image is the target type.
Optionally, the method further includes:
identifying whether the type of the query word to be identified is the target type or not according to the query word classification model;
and if so, identifying the type of the image in the target query result corresponding to the query word to be identified according to the image classification model.
Optionally, if the target type is a sensitive type, identifying, according to the image classification model, a type of an image in a target query result corresponding to the query term to be identified includes:
and if the target query result comprises the image of the sensitive type, canceling the display of the image of the sensitive type in the target query result.
Optionally, the method further includes:
and determining a determination condition adopted when the image classification model identifies the sensitive type according to the sensitive grade corresponding to the sensitive type of the query word to be identified.
Optionally, the determining, as the historical query term of the target type, the historical query term corresponding to the historical query result including the image of the target type includes:
and determining the historical query words corresponding to the historical query results which comprise the images of the target types and the ratio of the images of the target types meets the preset conditions as the historical query words of the target types.
In a second aspect, an embodiment of the present application provides an apparatus for determining a query term classification model, where the apparatus includes a first recognition unit, a type determination unit, and a first training unit:
the first identification unit is used for identifying whether the historical query result corresponding to the historical query word comprises the image of the target type according to the image classification model;
the type determining unit is used for determining a historical query word corresponding to a historical query result of the image with the target type as the historical query word of the target type;
the first training unit is used for training a query term classification model according to the historical query terms of the target type, and the query term classification model is used for identifying whether the type of the query terms is the target type.
Optionally, the apparatus further includes an obtaining unit and a second training unit:
the acquisition unit is used for acquiring the image set of the target type;
the second training unit is used for training the image classification model according to the image set, and the image classification model is used for identifying whether the type of the image is the target type.
Optionally, the apparatus further includes a second identifying unit and a third identifying unit:
the second identification unit is used for identifying whether the type of the query word to be identified is the target type according to the query word classification model; if the identification result is yes, triggering a third identification unit;
and the third identification unit is used for identifying the type of the image in the target query result corresponding to the query word to be identified according to the image classification model.
Optionally, if the target type is a sensitive type, the third identifying unit is further configured to cancel presentation of the image of the sensitive type in the target query result if the target query result includes the image of the sensitive type.
Optionally, the apparatus further includes a condition determining unit:
and the condition determining unit is used for determining a determining condition adopted when the image classification model identifies the sensitive type according to the sensitive grade corresponding to the sensitive type of the query word to be identified.
Optionally, the type determining unit is further configured to determine a historical query term corresponding to a historical query result that includes the image of the target type and in which the ratio of the image of the target type meets a predetermined condition as the historical query term of the target type.
In a third aspect, an embodiment of the present application provides a device for determining a query term classification model, including a memory, and one or more programs, where the one or more programs are stored in the memory, and configured to be executed by the one or more processors, where the one or more programs include instructions for:
identifying whether the historical query result corresponding to the historical query word comprises an image of a target type or not according to the image classification model;
determining a historical query word corresponding to a historical query result comprising the image of the target type as the historical query word of the target type;
and training a query term classification model according to the historical query terms of the target type, wherein the query term classification model is used for identifying whether the type of the query term is the target type.
In a fourth aspect, embodiments of the present application provide a machine-readable medium having stored thereon instructions, which when executed by one or more processors, cause an apparatus to perform the method for determining a query term classification model according to any one or more of the first aspect.
According to the technical scheme, the images in the historical query results are identified through the image classification model, and if one historical query result comprises the image of the target type, the type of the historical query word corresponding to the historical query result is determined to be the target type. The recognized historical query words of the target type can be used for training a query word classification model, so that the query word classification model can realize the function of recognizing whether the type of the query words is the target type. When the type of the query word needs to be determined to be the target type, manual labeling is not needed, and the method can be realized directly through the query word classification model, so that the identification efficiency of the type of the query word is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a flowchart of a method for determining a query term classification model according to an embodiment of the present application;
fig. 2 is a device configuration diagram of a query term classification model determination device according to an embodiment of the present application;
fig. 3 is a structural diagram of a query term classification model determining apparatus according to an embodiment of the present application;
fig. 4 is a block diagram of a server according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described below with reference to the accompanying drawings.
Because the efficiency is low through the mode of manually identifying and marking the types of the query words, the method can not keep up with the updating speed of the query words used by the user, and is difficult to be suitable for the current network search requirement.
To this end, the present application provides a method for determining a query term classification model, which may be applied to an electronic device with image and data processing capabilities, for example, a personal computer, a server, and the like.
In the embodiment of the application, the images in the historical query results are identified through an image classification model, the image classification model is mainly used for identifying whether the type of the images is a target type, and if one historical query result comprises the images of the target type, the type of the historical query word corresponding to the historical query result is determined to be the target type. The image classification model may be stored locally in the electronic device, or the image classification model may also be stored in a network location or other devices that can be called by the electronic device.
After the historical query word of the target type is identified through the type of the image, a query word classification model can be trained according to the historical query word, so that the query word classification model can realize the function of identifying whether the type of the query word is the target type. When the type of the query word needs to be determined to be the target type, manual labeling is not needed, and the method can be realized directly through the query word classification model, so that the identification efficiency of the type of the query word is improved.
The scheme provided by the embodiment of the application is described in the following with reference to the attached drawings. Fig. 1 is a flowchart of a method for determining a query term classification model according to an embodiment of the present application, where the method includes:
s101: and identifying whether the historical query result corresponding to the historical query word comprises the image of the target type according to an image classification model.
The historical query term may be a query term used when a user or a plurality of users query through a search engine, the number of the historical query terms is generally a plurality, and a historical query term may include a term, such as "car", or a plurality of terms, such as "car black box". The historical query results can be query results obtained by a user through historical query terms, and one historical query term corresponds to one historical query result. The historical query results may include other data content in addition to the images.
In any one of the historical query results, at least one image may be included, and whether the image included in the historical query result is of the target type may be identified by the image classification model.
In the embodiment of the present application, the type of the image may be a type of content displayed by the image, for example, a type of an image displaying a car may be a car type, and a type of an image displaying sensitive content may be a sensitive type.
The types can be obtained by pre-dividing, and the dividing granularity can be adjusted according to actual requirements. The object type in the embodiments of the present application may be a certain type that needs to be recognized.
After the image passes through the image classification model, the possibility of whether the image is of the target type can be obtained, and the possibility can be embodied in different forms such as probability or percentage. Whether the image is of the target type or not can be determined through a preset condition, wherein the preset condition can be a high probability and can be determined according to different scene requirements.
For example, if the preset condition is greater than 50%, if the probability that an image is identified as the target type by the image classification model is 30%, it may be determined that the type of the image is not the target type; if the probability that an image is identified as the target type by the image classification model is 60%, it can be determined that the type of the image is the target type.
It should be noted that the image classification model may be trained from a set of images of the target type.
The set of images of the target type includes a plurality of images of the target type. The images in the image set can be obtained by pre-classification or by crawling a specific type of website. For example, when the target type is an automobile type, the image can be obtained by crawling an automobile forum, an automobile website and the like, and since most of the images provided by the specific types of websites, such as the automobile forum and the automobile website, are images of the automobile type, a large proportion of images belonging to the automobile type can be obtained by crawling.
After the set of images of the target type is obtained, an image classification model may be trained from the set of images. Therefore, the image classification model obtained through training can identify whether the type of the image is the target type. In the training process, the images of the target type and the images of the non-target type can be used for training so as to improve the identification precision of the image classification model.
S102: and determining the historical query words corresponding to the historical query results including the images of the target type as the historical query words of the target type.
When an image of a target type is included in one historical query result, it may be considered that the type of the historical query term corresponding to the historical query result may be the target type.
The type of query term may embody the user's query intent, which is directly associated with which types of images may appear in the query results. For example, when the type of a query term is a car type, there is a high probability that an image of the car type appears in a query result obtained by the query term, or the proportion of the car type image in the image is high.
Therefore, when the image of the target type is identified in the historical query result, the type of the historical query word corresponding to the historical query result can be considered as the target type.
When the search engine queries according to the query term, some images which are not in accordance with the actual query requirement of the query term may exist in the acquired images. Therefore, in order to improve the accuracy, the historical query result can also include the image of the target type, and the historical query word corresponding to the historical query result is determined to be the target type under the condition that the proportion of the image of the target type meets the preset condition. The predetermined condition may be a predetermined proportional or quantitative value, such as 40% or 50, etc. Therefore, when a historical query term of a target type is determined, the probability that the actual query requirement of the historical query term meets the target type is higher.
S103: and training a query term classification model according to the historical query terms of the target type.
Since the query term classification model is trained according to the historical query terms determined in S102, and the historical query terms are all of the target type, the query term classification model obtained through training of the historical query terms can identify whether the type of the query term is the target type. In the training process, the target type historical query words and the non-target type historical query words can be adopted for training, so that the identification precision of the query word classification model is improved.
Therefore, the images in the historical query results are identified through the image classification model, and if one historical query result comprises the image of the target type, the type of the historical query word corresponding to the historical query result is determined to be the target type. The recognized historical query words of the target type can be used for training a query word classification model, so that the query word classification model can realize the function of recognizing whether the type of the query words is the target type. When the type of the query word needs to be determined to be the target type, manual labeling is not needed, and the method can be realized directly through the query word classification model, so that the identification efficiency of the type of the query word is improved.
The above embodiments mainly describe the determination method of the query term classification model, including how to obtain the training data and the process of training the model. Next, a specific application of the query classification model will be described on the basis of the embodiment shown in fig. 1.
When the search engine acquires the query term currently input by the user, the search engine may identify the current query term through the query term classification model acquired in S103 to determine whether the current query term is of the target type. The search engine described herein may be configured in a terminal used by a user, or may be configured in a server to which the terminal used by the user has a data connection.
Next, a specific application of the query classification model is described by taking the query term to be identified as the current query term.
It should be noted that the query term to be identified may include one term or a plurality of terms, for example, when the user currently inputs the query term "airplane" for querying, the "airplane" may be used as the query term to be identified; when the user currently inputs the query word 'airplane propeller' for query, the 'airplane propeller' can be used as the query word to be identified.
When the query word to be recognized currently input by the user is obtained, the type of the query word to be recognized can be recognized through the query word classification model so as to determine whether the query word to be recognized is the target type.
After the query word to be recognized passes through the query word classification model, the possibility of whether the query word to be recognized is of the target type can be obtained, and the possibility can be embodied in different forms such as probability or percentage. Whether the query word to be recognized is the target type or not can be determined through a preset condition, wherein the preset condition can be a high probability and can be determined according to different scene requirements.
For example, when the preset condition is greater than 50%, if the probability that the query word to be recognized is recognized as the target type through the query word classification model is 30%, it may be determined that the type of the query word to be recognized is not the target type; if the probability that the query word to be recognized is recognized as the target type through the query word classification model is 60%, it may be determined that the type of the query word to be recognized is the target type.
If the query word to be recognized is recognized as the target type, the query requirement and the purpose of inputting the query word to be recognized by the user are determined. The search engine can further optimize the target query result corresponding to the query word to be identified based on the query requirement and purpose of the user. Specifically, the type of the image in the target query result corresponding to the query word to be identified can be identified according to the image classification model. Wherein the image classification model may be the one used in S101.
Because the target query result comprises the image, before the target query result is displayed to the user, the type of the image in the target query result can be identified through the image classification model so as to determine the image which is specifically of the target type, so that when the target query result is displayed to the user, the display of the image which is not of the target type can be cancelled, or the display of the image of the target type can be cancelled.
For example, when the target type is an automobile type, an image of the automobile type can be identified from the target query result through the image classification model, and when the target query result is displayed to a user, the display of the image of the non-automobile type can be cancelled, so that the displayed image can be expected to better meet the query requirement and purpose of the user.
The target type may also be a sensitive type, which may be pornography, gambling, reaction, etc. The query requirement of the type is met and needs to be controlled, and the diffusion of bad information is avoided. Therefore, when the target type is the sensitive type, the search engine can identify the sensitive type image in the target query result through the image classification model, and when the target query result is displayed to the user, the display of the sensitive type image can be cancelled, and only the non-sensitive type image is displayed, so that the displayed image is expected to avoid the influence of bad information on the user.
In some application scenarios, in addition to determining whether the type of the query word to be recognized is a sensitive type, a sensitivity level corresponding to the sensitive type of the query word to be recognized may also be determined. The sensitivity level may identify a degree of sensitivity that the query term to be recognized may embody. The sensitivity level of the query word to be identified can be determined according to the sensitivity type probability of the query word to be identified, which is obtained by the query word classification model, and can also be determined in other modes.
When the query word to be identified is a sensitive type but the sensitivity level is not high, the filtering standard can be relaxed when filtering the image in the target query result, and some images which are not sensitive but meet the query requirement of the user in the target query result are displayed to the user so as to meet the query requirement of the user.
Therefore, in the embodiment of the application, the determination condition adopted when the image classification model identifies the sensitive type can be determined according to the sensitive grade corresponding to the sensitive type of the query word to be identified. For example, for a lower sensitivity level, the determination condition adopted by the image classification model when identifying the sensitivity type may be looser, and for a higher sensitivity level, the determination condition adopted by the image classification model when identifying the sensitivity type may be tighter. Therefore, under different sensitivity levels, the result that the same image is identified as a sensitive type by the image classification model can be different. For example, for a query word to be recognized with a lower sensitivity level, the image classification model identifies an image with a higher probability of a sensitive type as the sensitive type, and an image with a lower probability of the sensitive type will not be identified as the sensitive type. For the query words to be identified with higher sensitivity levels, the image classification model not only identifies the images with higher probability of the sensitivity types as the sensitivity types, but also identifies the images with lower probability of the sensitivity types as the sensitivity types.
Fig. 2 is a block diagram of an apparatus for determining a query term classification model according to an embodiment of the present application, where the apparatus includes a first recognition unit 201, a type determination unit 202, and a first training unit 203:
the first identifying unit 201 is configured to identify whether a history query result corresponding to a history query term includes an image of a target type according to an image classification model;
the type determining unit 202 is configured to determine a history query term corresponding to a history query result including the image of the target type as the history query term of the target type;
the first training unit 203 is configured to train a query term classification model according to the historical query terms of the target type, where the query term classification model is used to identify whether the type of the query term is the target type.
Optionally, the apparatus further includes an obtaining unit and a second training unit:
the acquisition unit is used for acquiring the image set of the target type;
the second training unit is used for training the image classification model according to the image set, and the image classification model is used for identifying whether the type of the image is the target type.
Optionally, the apparatus further includes a second identifying unit and a third identifying unit:
the second identification unit is used for identifying whether the type of the query word to be identified is the target type according to the query word classification model; if the identification result is yes, triggering a third identification unit;
and the third identification unit is used for identifying the type of the image in the target query result corresponding to the query word to be identified according to the image classification model.
Optionally, if the target type is a sensitive type, the third identifying unit is further configured to cancel presentation of the image of the sensitive type in the target query result if the target query result includes the image of the sensitive type.
Optionally, the apparatus further includes a condition determining unit:
and the condition determining unit is used for determining a determining condition adopted when the image classification model identifies the sensitive type according to the sensitive grade corresponding to the sensitive type of the query word to be identified.
Optionally, the type determining unit is further configured to determine a historical query term corresponding to a historical query result that includes the image of the target type and in which the ratio of the image of the target type meets a predetermined condition as the historical query term of the target type.
Therefore, in the embodiment of the application, the determination condition adopted when the image classification model identifies the sensitive type can be determined according to the sensitive grade corresponding to the sensitive type of the query word to be identified. For example, for a lower sensitivity level, the determination condition adopted by the image classification model when identifying the sensitivity type may be looser, and for a higher sensitivity level, the determination condition adopted by the image classification model when identifying the sensitivity type may be tighter. Therefore, under different sensitivity levels, the result that the same image is identified as a sensitive type by the image classification model can be different. For example, for a query word to be recognized with a lower sensitivity level, the image classification model identifies an image with a higher probability of a sensitive type as the sensitive type, and an image with a lower probability of the sensitive type will not be identified as the sensitive type. For the query words to be identified with higher sensitivity levels, the image classification model not only identifies the images with higher probability of the sensitivity types as the sensitivity types, but also identifies the images with lower probability of the sensitivity types as the sensitivity types.
Fig. 3 is a block diagram illustrating an apparatus 300 for determining a query term classification model according to an example embodiment. For example, the apparatus 300 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
Referring to fig. 3, the apparatus 300 may include one or more of the following components: processing component 302, memory 304, power component 306, multimedia component 308, audio component 310, input/output (I/O) interface 312, sensor component 314, and communication component 316.
The processing component 302 generally controls overall operation of the device 300, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing elements 302 may include one or more processors 320 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 302 can include one or more modules that facilitate interaction between the processing component 302 and other components. For example, the processing component 302 can include a multimedia module to facilitate interaction between the multimedia component 308 and the processing component 302.
The memory 304 is configured to store various types of data to support operations at the device 300. Examples of such data include instructions for any application or method operating on device 300, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 304 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 306 provides power to the various components of the device 300. The power components 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the apparatus 300.
The multimedia component 308 includes a screen that provides an output interface between the device 300 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 308 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 300 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 310 is configured to output and/or input audio signals. For example, audio component 310 includes a Microphone (MIC) configured to receive external audio signals when apparatus 300 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 304 or transmitted via the communication component 316. In some embodiments, audio component 310 also includes a speaker for outputting audio signals.
The I/O interface 312 provides an interface between the processing component 302 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 314 includes one or more sensors for providing various aspects of status assessment for the device 300. For example, sensor assembly 314 may detect an open/closed state of device 300, the relative positioning of components, such as a display and keypad of apparatus 300, the change in position of apparatus 300 or a component of apparatus 300, the presence or absence of user contact with apparatus 300, the orientation or acceleration/deceleration of apparatus 300, and the change in temperature of apparatus 300. Sensor assembly 314 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 314 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 316 is configured to facilitate wired or wireless communication between the apparatus 300 and other devices. The device 300 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication section 316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 300 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
Fig. 4 is a schematic structural diagram of a server in an embodiment of the present invention. The server 400 may vary significantly due to configuration or performance, and may include one or more Central Processing Units (CPUs) 422 (e.g., one or more processors) and memory 432, one or more storage media 430 (e.g., one or more mass storage devices) storing applications 442 or data 444. Wherein the memory 432 and storage medium 430 may be transient or persistent storage. The program stored on the storage medium 430 may include one or more modules (not shown), each of which may include a series of instruction operations for the server. Still further, the central processor 422 may be arranged to communicate with the storage medium 430, and execute a series of instruction operations in the storage medium 430 on the server 400.
The server 400 may also include one or more power supplies 426, one or more wired or wireless network interfaces 450, one or more input-output interfaces 458, one or more keyboards 456, and/or one or more operating systems 441, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and so forth.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 304 comprising instructions, executable by the processor 320 of the apparatus 300 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
A non-transitory computer-readable storage medium having instructions therein, which when executed by a processor of a mobile terminal, enable the mobile terminal to perform a method of determining a query term classification model, the method comprising:
identifying whether the historical query result corresponding to the historical query word comprises an image of a target type or not according to the image classification model;
determining a historical query word corresponding to a historical query result comprising the image of the target type as the historical query word of the target type;
and training a query term classification model according to the historical query terms of the target type, wherein the query term classification model is used for identifying whether the type of the query term is the target type.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium may be at least one of the following media: various media that can store program codes, such as read-only memory (ROM), RAM, magnetic disk, or optical disk.
It should be noted that, in the present specification, all the embodiments are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus and system embodiments, since they are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only one specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A method for determining a query term classification model, the method comprising:
identifying whether the historical query result corresponding to the historical query word comprises an image of a target type or not according to the image classification model;
determining a historical query word corresponding to a historical query result comprising the image of the target type as the historical query word of the target type;
and training a query term classification model according to the historical query terms of the target type, wherein the query term classification model is used for identifying whether the type of the query term is the target type.
2. The method of claim 1, further comprising:
acquiring an image set of the target type;
and training the image classification model according to the image set, wherein the image classification model is used for identifying whether the type of the image is the target type.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
identifying whether the type of the query word to be identified is the target type or not according to the query word classification model;
and if so, identifying the type of the image in the target query result corresponding to the query word to be identified according to the image classification model.
4. The method according to claim 3, wherein if the target type is a sensitive type, the identifying the type of the image in the target query result corresponding to the query term to be identified according to the image classification model comprises:
and if the target query result comprises the image of the sensitive type, canceling the display of the image of the sensitive type in the target query result.
5. The method of claim 4, further comprising:
and determining a determination condition adopted when the image classification model identifies the sensitive type according to the sensitive grade corresponding to the sensitive type of the query word to be identified.
6. The method according to claim 1, wherein the determining the historical query term corresponding to the historical query result including the image of the target type as the historical query term of the target type includes:
and determining the historical query words corresponding to the historical query results which comprise the images of the target types and the ratio of the images of the target types meets the preset conditions as the historical query words of the target types.
7. An apparatus for determining a query term classification model, the apparatus comprising a first recognition unit, a type determination unit, and a first training unit:
the first identification unit is used for identifying whether the historical query result corresponding to the historical query word comprises the image of the target type according to the image classification model;
the type determining unit is used for determining a historical query word corresponding to a historical query result of the image with the target type as the historical query word of the target type;
the first training unit is used for training a query term classification model according to the historical query terms of the target type, and the query term classification model is used for identifying whether the type of the query terms is the target type.
8. The apparatus of claim 7, further comprising an acquisition unit and a second training unit:
the acquisition unit is used for acquiring the image set of the target type;
the second training unit is used for training the image classification model according to the image set, and the image classification model is used for identifying whether the type of the image is the target type.
9. An apparatus for determining a query term classification model, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory, and wherein the one or more programs configured to be executed by the one or more processors comprise instructions for:
identifying whether the historical query result corresponding to the historical query word comprises an image of a target type or not according to the image classification model;
determining a historical query word corresponding to a historical query result comprising the image of the target type as the historical query word of the target type;
and training a query term classification model according to the historical query terms of the target type, wherein the query term classification model is used for identifying whether the type of the query term is the target type.
10. A machine-readable medium having stored thereon instructions, which when executed by one or more processors, cause an apparatus to perform a method of determining a query term classification model as recited in one or more of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811243106.9A CN111177521A (en) | 2018-10-24 | 2018-10-24 | Method and device for determining query term classification model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811243106.9A CN111177521A (en) | 2018-10-24 | 2018-10-24 | Method and device for determining query term classification model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111177521A true CN111177521A (en) | 2020-05-19 |
Family
ID=70653487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811243106.9A Pending CN111177521A (en) | 2018-10-24 | 2018-10-24 | Method and device for determining query term classification model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111177521A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666317A (en) * | 2020-07-06 | 2020-09-15 | 腾讯科技（深圳）有限公司 | Cheating information mining method and cheating information identification method and device |
| CN112989089A (en) * | 2021-02-22 | 2021-06-18 | 北京三一智造科技有限公司 | Element state query method and device, electronic equipment and storage medium |
| CN113204667A (en) * | 2021-04-13 | 2021-08-03 | 北京百度网讯科技有限公司 | Method and device for training audio labeling model and audio labeling |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095187A (en) * | 2015-08-07 | 2015-11-25 | 广州神马移动信息科技有限公司 | Search intention identification method and device |
| CN105243135A (en) * | 2015-09-30 | 2016-01-13 | 百度在线网络技术（北京）有限公司 | Method and apparatus for showing search result |
| CN106844472A (en) * | 2016-12-22 | 2017-06-13 | 北京搜狗科技发展有限公司 | A kind of searching method and device, a kind of device for searching for |
| CN106997379A (en) * | 2017-03-20 | 2017-08-01 | 杭州电子科技大学 | A kind of merging method of the close text based on picture text click volume |
| CN107423304A (en) * | 2016-05-24 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Term sorting technique and device |
| CN107526769A (en) * | 2017-07-10 | 2017-12-29 | 北京百度网讯科技有限公司 | Photo processing method and device, equipment and computer-readable recording medium based on artificial intelligence |
| CN108363928A (en) * | 2018-02-08 | 2018-08-03 | 广西师范大学 | The adaptive differential method for secret protection being associated in medical data |
-
2018
- 2018-10-24 CN CN201811243106.9A patent/CN111177521A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105095187A (en) * | 2015-08-07 | 2015-11-25 | 广州神马移动信息科技有限公司 | Search intention identification method and device |
| CN105243135A (en) * | 2015-09-30 | 2016-01-13 | 百度在线网络技术（北京）有限公司 | Method and apparatus for showing search result |
| CN107423304A (en) * | 2016-05-24 | 2017-12-01 | 百度在线网络技术（北京）有限公司 | Term sorting technique and device |
| CN106844472A (en) * | 2016-12-22 | 2017-06-13 | 北京搜狗科技发展有限公司 | A kind of searching method and device, a kind of device for searching for |
| CN106997379A (en) * | 2017-03-20 | 2017-08-01 | 杭州电子科技大学 | A kind of merging method of the close text based on picture text click volume |
| CN107526769A (en) * | 2017-07-10 | 2017-12-29 | 北京百度网讯科技有限公司 | Photo processing method and device, equipment and computer-readable recording medium based on artificial intelligence |
| CN108363928A (en) * | 2018-02-08 | 2018-08-03 | 广西师范大学 | The adaptive differential method for secret protection being associated in medical data |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666317A (en) * | 2020-07-06 | 2020-09-15 | 腾讯科技（深圳）有限公司 | Cheating information mining method and cheating information identification method and device |
| CN112989089A (en) * | 2021-02-22 | 2021-06-18 | 北京三一智造科技有限公司 | Element state query method and device, electronic equipment and storage medium |
| CN113204667A (en) * | 2021-04-13 | 2021-08-03 | 北京百度网讯科技有限公司 | Method and device for training audio labeling model and audio labeling |
| CN113204667B (en) * | 2021-04-13 | 2024-03-22 | 北京百度网讯科技有限公司 | Method and device for training audio annotation model and audio annotation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105338409B (en) | Network video preloading method and device | |
| US20180121040A1 (en) | Method and device for managing notification messages | |
| CN105068976B (en) | Ticket information display method and device | |
| CN106897937B (en) | Method and device for displaying social sharing information | |
| CN107315487B (en) | Input processing method and device and electronic equipment | |
| US20160314164A1 (en) | Methods and devices for sharing cloud-based business card | |
| CN106331328B (en) | Information prompting method and device | |
| CN111177521A (en) | Method and device for determining query term classification model | |
| CN108230094B (en) | Vehicle recommendation method and device | |
| CN107402767B (en) | Method and device for displaying push message | |
| CN105488074B (en) | Photo clustering method and device | |
| CN110213062B (en) | Method and device for processing message | |
| CN109842688B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| US20170289326A1 (en) | Methods and Apparatuses for Interpreting a Phone Number | |
| CN109799916B (en) | Candidate item association method and device | |
| CN109145151B (en) | Video emotion classification acquisition method and device | |
| CN107908729B (en) | Interface display method and device | |
| CN108012258B (en) | Data traffic management method and device for virtual SIM card, terminal and server | |
| CN110020082B (en) | Searching method and device | |
| CN108108356B (en) | Character translation method, device and equipment | |
| US20170169467A1 (en) | Information push method and device | |
| CN110362760B (en) | Method, device and medium for intelligently prompting search results | |
| CN112083811B (en) | Candidate item display method and device | |
| CN110417987B (en) | Operation response method, device, equipment and readable storage medium | |
| CN107257384B (en) | Service state monitoring method and 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 |