CN111680517A - Method, apparatus, device and storage medium for training a model - Google Patents
Method, apparatus, device and storage medium for training a model Download PDFInfo
- Publication number
- CN111680517A CN111680517A CN202010524463.3A CN202010524463A CN111680517A CN 111680517 A CN111680517 A CN 111680517A CN 202010524463 A CN202010524463 A CN 202010524463A CN 111680517 A CN111680517 A CN 111680517A
- Authority
- CN
- China
- Prior art keywords
- intention
- training
- sample data
- sample
- labeling
- 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.)
- Granted
Links
- 238000012549 training Methods 0.000 title claims abstract description 261
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000002372 labelling Methods 0.000 claims abstract description 114
- 238000012545 processing Methods 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 19
- 230000004044 response Effects 0.000 claims description 9
- 230000004048 modification Effects 0.000 claims description 5
- 238000012986 modification Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 238000013135 deep learning Methods 0.000 abstract description 2
- 238000003058 natural language processing Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 239000003795 chemical substances by application Substances 0.000 description 7
- 238000004891 communication Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 235000019580 granularity Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Databases & Information Systems (AREA)
- Manipulator (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application discloses a method, a device, equipment and a storage medium for training a model, and relates to the fields of natural language processing and deep learning. The specific implementation scheme is as follows: acquiring a first training sample set and a second training sample set; predicting the first sample data by using a first intention recognition model, and determining confidence degrees corresponding to all prediction intents; determining a third training sample set according to the first labeling intention, the confidence degrees corresponding to the prediction intents, the second sample data and the corresponding second labeling intention; the second intent recognition model is trained based on a third set of training samples. The implementation mode can make full use of historical data used for establishing the man-machine conversation robot, reduce the cost of the newly-built man-machine conversation robot, and improve the intention recognition effect of the newly-built man-machine conversation robot under the condition of a small amount of labeled samples.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to the field of natural language processing and deep learning technologies, and in particular, to a method, an apparatus, a device, and a storage medium for training a model.
Background
Intent recognition is one of the core functions of a human-machine dialog robot, typically implemented using an intent recognition model. While the effectiveness of the intent recognition model depends heavily on the quantity and quality of the training data. The more samples in the training data are, the higher the labeling quality is, and the better the effect of the obtained intention recognition model is. Manually labeled intention dialogue samples have high data quality, but are difficult to scale due to the high labeling cost.
With the rise of human-computer interaction robots, various human-computer interaction robots are established for different applications, and the intentions of the human-computer interaction robots are deeply customized on application scenes basically. Therefore, the human-machine interaction robots in different application scenarios have different intention classification granularities, different intention names, and the like. Thus, when a new application scene is faced, the data of the man-machine interaction robot established before is difficult to be reused.
Disclosure of Invention
A method, apparatus, device, and storage medium for training a model are provided.
According to a first aspect, there is provided a method for training a model, comprising: acquiring a first training sample set and a second training sample set, wherein the first training sample set comprises first sample data and a corresponding first labeling intention, and the second training sample set comprises second sample data and a corresponding second labeling intention; acquiring a trained first intention recognition model and a second intention recognition model to be trained; predicting the first sample data by using a first intention recognition model, and determining confidence degrees corresponding to all prediction intents; determining a third training sample set according to the first labeling intention, the confidence degrees corresponding to the prediction intents, the second sample data and the corresponding second labeling intention; the second intent recognition model is trained based on a third set of training samples.
According to a second aspect, there is provided an apparatus for training a model, comprising: the device comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is configured to acquire a first training sample set and a second training sample set, the first training sample set comprises first sample data and corresponding first labeling intents, and the second training sample set comprises second sample data and corresponding second labeling intents; a second acquisition unit configured to acquire the trained first intention recognition model and a second intention recognition model to be trained; a confidence degree determining unit configured to predict the first sample data by using the first intention recognition model, and determine a confidence degree corresponding to each prediction intention; the sample generation unit is configured to determine a third training sample set according to the first labeling intention, the confidence degree corresponding to each prediction intention, the second sample data and the corresponding second labeling intention; a first model training unit configured to train a second intent recognition model according to a third set of training samples.
According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in the first aspect.
According to a fourth aspect, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method as described in the first aspect.
According to the technology of the application, historical data used for establishing the man-machine conversation robot can be fully utilized, the cost of the newly-built man-machine conversation robot is reduced, and the intention recognition effect of the newly-built man-machine conversation robot is improved under the condition of a small number of labeled samples.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for training a model according to the present application;
FIG. 3 is a schematic diagram of an application scenario of a method for training a model according to the present application;
FIG. 4 is a flow diagram of another embodiment of a method for training a model according to the present application;
FIG. 5 is a flow diagram of yet another embodiment of a method for training a model according to the present application;
FIG. 6 is a schematic block diagram of one embodiment of an apparatus for training models according to the present application;
FIG. 7 is a block diagram of an electronic device for implementing a method for training a model according to an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the present method for training a model or apparatus for training a model may be applied.
As shown in fig. 1, the system architecture 100 may include intelligent end devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the intelligent terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the intelligent terminal device 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various communication client applications, such as a voice recognition application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like, may be installed on the intelligent terminal devices 101, 102, 103.
The intelligent terminal devices 101, 102, 103 may be hardware or software. When the smart terminal 101, 102, 103 is hardware, it can be various electronic devices with voice recognition function, including but not limited to smart phones, smart speakers, smart robots, etc. When the smart terminal 101, 102, 103 is software, it can be installed in the electronic devices listed above. It may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a background server that provides a human-machine conversation robot for the intelligent terminal devices 101, 102, 103. The background server may analyze and perform other processing on the data such as the voice received by the terminal devices 101, 102, and 103, and feed back the processing result (for example, response data) to the intelligent terminal devices 101, 102, and 103.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be noted that the method for training the model provided in the embodiment of the present application is generally performed by the server 105. Accordingly, the means for training the model is typically located in the server 105.
It should be understood that the number of intelligent end devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of intelligent end devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for training a model according to the present application is shown. The method for training the model of the embodiment comprises the following steps:
In this embodiment, an executing agent (e.g., the server 105 shown in fig. 1) of the method for training the model may obtain a first training sample set and a second training sample set. The first training sample set comprises first sample data and corresponding first labeling intents, and the second training sample set comprises second sample data and corresponding second labeling intents. Here, the sample data in the first training sample set may be sample data for a new domain, and the number thereof may be small. Because the manual annotation data consumption period is long and the cost is high, only a small amount of annotation data is acquired, so that the cost is reduced, and the efficiency is improved. The second set of training samples may include general sample data or historical sample data used in other fields, and the amount of sample data included in the second set of training samples may be very large. The sample data may be a plurality of dialog turns or a text. Each sample data corresponds to a labeling intention. The annotation intent can include audio and video requirements, search requirements, and the like.
It will be appreciated that the first set of training samples and the second set of training samples may include data that partially overlap, and as such, the first annotation intent may partially overlap the second annotation intent.
In this embodiment, the executing subject may further obtain a trained first intention recognition model and a second intention recognition model to be trained. Here, the first intention recognition model may be a general intention recognition model, and may also be an intention recognition model of other application fields. The second intent recognition model may be an intent recognition model applied to the new domain. It can be appreciated that the first intent recognition model is less accurate when applied to a new domain.
In this embodiment, the first intention recognition model may be utilized to predict the sample data, that is, the sample data in the first sample training sample set is input into the first intention recognition model. The confidence corresponding to each prediction intention of the sample data can be obtained. For example, for sample data a, the results output by the first intent recognition model may include: the intent 1 confidence is 0.2, the intent 2 confidence is 0.4, the intent 3 confidence is 0.3, and the intent 4 confidence is 0.3. For sample data B, the results output by the first intent recognition model may include: intent 5 confidence is 0.7. Each of the predicted intents may be considered herein as an intent tag for the first sample data.
Conventional supervised learning typically assumes that each sample data is associated with a unique one of the labels. However, in many practical tasks, one sample data typically possesses multiple tags. For example, in text classification, if a document is classified, the olympics belong to both business and sports; in image annotation, an image in a paris scene is associated with both the tower and the sky. In this embodiment, each intention label corresponding to the first sample data can be obtained by the first intention recognition model.
It is understood that the number of resulting prediction intents is at least one. The first annotation intention may or may not be included in each predicted intention.
And 204, determining a third training sample set according to the first labeling intention, the confidence degrees corresponding to the prediction intents, the second sample data and the corresponding second labeling intention.
In this embodiment, after obtaining the confidence degrees corresponding to the prediction intents, a third training sample set may be determined by combining the first annotation intention, the second sample data, and the corresponding second annotation intention. Specifically, the prediction intent with the highest confidence may be determined first. And then, taking out second sample data corresponding to a second labeling intention which is the same as the prediction intention in the second training sample set. And modifying the second labeling intention of the taken sample data into the first labeling intention to obtain a third training sample set. For example, the first labeled intention is intention 1, and the confidence degrees corresponding to the prediction intents are: the intent 1 confidence is 0.2, the intent 2 confidence is 0.4, the intent 3 confidence is 0.3, and the intent 4 confidence is 0.3. It may be determined that the confidence of intent 2 is highest in the predicted intent. Then, sample data corresponding to fig. 2 in the second training sample set may be fetched. And modifying the labeling intention of the taken sample data into intention 1. Thus, a new sample data corresponding to fig. 1, i.e. a third training sample set, is obtained. Here, the third set of training samples is an extension of the first set of training samples.
After the third set of training samples is obtained, the second intent recognition model may be trained using the third set of training samples. It is to be understood that each sample data in the third set of training samples corresponds to at least one intention tag. Thus, the result output by the second intent recognition model also includes at least one intent tag.
Referring to FIG. 3, a schematic diagram of an application scenario of the method for training a model of the present application is shown. In the application scenario of fig. 3, the server 301 obtains historical annotation data applied to the medical field, the architectural field, and the financial field from the database 302. Meanwhile, the server 301 acquires a small amount of annotation data applied to a new field (legal field) from the terminal device 303. Through the processing of the steps 202-205, an intention recognition model applied to the legal field is obtained through training. The server 301 may return the above-described intention recognition model to the terminal device 303 to cause the technician to apply the above-described intention recognition model to the human-machine conversation robot.
The method for training the model provided by the embodiment of the application can make full use of historical data used for establishing the man-machine interactive robot, reduce the cost of the newly-built man-machine interactive robot, and improve the intention recognition effect of the newly-built man-machine interactive robot under the condition of a small number of labeled samples.
With continued reference to FIG. 4, a flow 400 of another embodiment of a method for training a model according to the present application is shown. As shown in fig. 4, the method for training a model of the present embodiment may include the following steps:
In this embodiment, the first training sample set may include a plurality of subsets, and sample data in each subset corresponds to the same labeling intention. Similarly, the second training sample set may also include a plurality of subsets, and the sample data in each subset corresponds to the same labeling intention.
In this embodiment, the execution subject may first process the sample data in the second training sample set. The above processing may include merging, deleting, modifying, and the like. Specifically, the execution subject may consider the number of second sample data corresponding to each second annotation intention when performing processing. For example, the second annotation intention and the corresponding second sample data, the number of which is less than the preset threshold, are deleted.
In some optional implementations of this embodiment, the executing entity may process the second set of training samples by:
step 4021, selecting a first training sample subset and a second training sample subset from the second training sample set.
In this implementation, the first training sample subset and the second training sample subset may be selected from the second training sample set at first. And the second labeling intentions corresponding to the first training sample subset and the second training sample subset are different, and the quantity of the second sample data in the first training sample subset is greater than that of the second sample data in the second training sample subset. That is, the first subset of training samples and the second subset of training samples are a set of second sample data corresponding to different second annotation intents. And the number of second sample data in the first subset of training samples is larger.
Step 4022, determining the number of common sample data of the first subset of training samples and the second subset of training samples.
After selecting the first subset of training samples and the second subset of training samples, the number of sample data common to the first subset of training samples and the second subset of training samples may be determined. Here, the common sample data is second sample data that exists in both the first training sample subset and the second training sample subset. The execution subject may count the common sample data to determine the number thereof.
And step 4023, determining whether the preset condition is met according to the number of the common sample data and the number of the second sample data in the second training sample subset.
Next, the number of sample data that the execution subject can share, the number of samples in the second subset of training samples, and whether the preset condition is satisfied is determined. The preset conditions may include, but are not limited to: the number of samples in the second subset of training samples is greater than or equal to a certain number threshold, and the number of common sample data is greater than or equal to a certain number threshold.
In some alternative implementations, whether the preset condition is satisfied may be determined by the following steps not shown in fig. 4: determining the ratio of the number of the common sample data to the number of the second sample data in the second training sample subset; in response to determining that the number of second sample data in the second subset of training samples is less than a first preset number threshold and the ratio is greater than a first preset proportion threshold, or that the ratio is greater than a second preset proportion threshold, determining that a preset condition is satisfied.
In this implementation, the executing agent may first determine a ratio of the number of common sample data to the number of second sample data in the second subset of training samples. The preset condition is considered to be satisfied if the number of second sample data in the second subset of training samples is greater than a first preset number threshold (e.g., 50) while the ratio is greater than a first preset proportion threshold. Or, the ratio is larger than a second preset ratio threshold value, and the preset condition is determined to be met.
Step 4024, in response to the preset condition being met, modifying the second labeling intention corresponding to the second training sample subset into the second labeling intention corresponding to the first training sample subset.
If it is determined that the preset condition is satisfied, the execution subject may modify the second labeling intention corresponding to the second subset of training samples into the second labeling intention corresponding to the first subset of training samples. In this way, the reduction and merging of the second sample data in the second training sample set can be realized.
In some optional implementations of this embodiment, the processing may further include the following steps not shown in fig. 4: and deleting the training sample subset of which the number of the second sample data is less than a second preset number threshold.
In this implementation, if the number of second sample data included in a certain subset in the second training sample set is too small, the subset is considered to be unavailable, and the second sample data in the subset and the corresponding second annotation intention can be deleted directly.
Through the processing, more sample data corresponding to each labeling intention in the second training sample set can be obtained, and the method is convenient for subsequent use.
And 403, training the initial intention recognition model by using the processed second training sample set to obtain a first intention recognition model.
The executing subject may train the initial intention recognition model using the processed second training sample set, resulting in a first intention recognition model. In particular, the executing agent may use the second sample data as an input of the initial intent recognition model and use the corresponding second annotation intent as an output of the initial intent recognition model. Here, the initial intention recognition model may be an initialized intention recognition model, that is, parameters in the intention recognition model are initialized values, and may also be a pre-trained intention recognition model.
It should be noted that the first steps 402 to 403 may be executed by an executing entity of the method for training a model of the present application, or may be implemented by other electronic devices. If implemented by other electronic devices, the other electronic devices may send the first intent recognition model to the executing agent.
In this embodiment, the second intention recognition model may be an intention recognition model having the same structure as the first intention recognition model but different parameters, or the second intention recognition model may be an intention recognition model having a different structure from the first intention recognition model. The domain to which the second intent recognition model applies may be different from the domain to which the first intent recognition model applies.
And 406, determining a third training sample set according to the first labeling intention, the confidence degrees corresponding to the prediction intents, the second sample data and the corresponding second labeling intention.
The principle of steps 405 to 407 is similar to that of steps 203 to 205, and is not described herein again.
According to the method for training the model provided by the embodiment of the application, the intention recognition model can be trained by using the historical annotation data, and then a new intention recognition model is trained based on the intention recognition model, so that the utilization rate of the historical annotation data is improved.
With continued reference to FIG. 5, a flow 500 of another embodiment of a method for training a model according to the present application is shown. As shown in fig. 5, the method for training a model of the present embodiment may include the following steps:
In this embodiment, the execution subject may determine, from the second training sample set, a second annotation intention that is similar to the first annotation intention according to the first annotation intention and the confidence degrees corresponding to the prediction intents. Specifically, the executing subject may search for a second prediction intention with a confidence degree greater than a preset threshold value in the training sample set, and use the searched second annotation intention as a second annotation intention similar to the first annotation intention.
In some alternative implementations of the embodiment, the performing agent may determine the second annotation intent that is similar to the first annotation intent by: for each first annotation intention, sorting the prediction intents in a high-to-low order according to the confidence degrees of the prediction intents of the first sample data corresponding to the first annotation intention; and regarding a second labeling intention related to the first preset number of prediction intents in the sequence in the second training sample set as a second labeling intention similar to the first labeling intention.
In this implementation, for each first annotation intention, the executing subject may first determine first sample data corresponding to the first annotation intention, and then determine a confidence of each prediction intention of each first sample data. And sequencing the confidence degrees according to the sequence from high to low. Then take the pre-set number (N) of predicted intents. And determining second labeling intents related to the first N predicted intents, and finally, regarding the second labeling intents as second labeling intents similar to the first labeling intents. Here, correlation means the same as or similar to the first N prediction intents.
And 505, selecting partial second sample data from the second sample data corresponding to the determined second labeling intention.
After determining the second labeling intents that are close to each other, the execution subject may select a part of second sample data from the second sample data corresponding to each second labeling intention. In the selection, the selection may be performed randomly, or multiple rounds of dialog pattern data may be selected preferentially. The number of the second sample data selected from the second sample data corresponding to each second labeling intention may be the same or different.
In some optional implementations of this embodiment, the execution subject may select part of the second sample data by: and for each determined second labeling intention, selecting second sample data from second sample data corresponding to the second labeling intention according to the ratio of the confidence degree corresponding to the prediction intention related to the second labeling intention to the sum of the confidence degrees corresponding to the prediction intents.
In this implementation, the executing agent may first calculate the sum of the confidence levels of the prediction intents, denoted as P. The ratio of the confidence of each prediction intent to the above sum is then calculated. Then, the execution subject may calculate a sum of the second sample data corresponding to each second annotation intention, which is denoted as M. For each determined second annotation intention, the executive body can select sample data according to the ratio corresponding to the prediction intention related to the second annotation intention. Specifically, the number of the second sample data is selected from the second sample data corresponding to the second labeling intention to be equal to P × M/P. Wherein p is the confidence of the prediction intent associated with the second annotation intent.
After the second sample data is selected, the execution subject may determine a third training sample set in combination with the second sample data and the first training sample set. Specifically, the execution subject may use the second annotation intention and the first training sample set corresponding to the selected second sample data as a third training sample set.
In some optional implementations of this embodiment, the performing agent may determine the third set of training samples by: modifying the second labeling intention of the selected second sample data into a similar first labeling intention; and determining a third training sample set according to the marking intention corresponding to the modified second sample data and the first training sample set.
In this implementation manner, the execution subject may modify the second annotation intention of the selected second sample data into the first annotation intention similar to the second annotation intention. In this way, the number of sample data corresponding to the first labeling intention is increased, and a third training sample set is obtained by combining the first sample data corresponding to each first labeling intention in the first training sample set. It is to be understood that the labeling intents included in the third training sample set are the same as the labeling intents in the first training sample set, and thus can be used for training of the second intention recognition model.
The method for training the model provided by the embodiment of the application can expand a small amount of labeled data in a new field by using historical labeled data, so that the utilization rate of the historical labeled data is improved.
With further reference to fig. 6, as an implementation of the method shown in the above figures, the present application provides an embodiment of an apparatus for training a model, which corresponds to the embodiment of the method shown in fig. 2, and which can be applied in various electronic devices.
As shown in fig. 6, the training model apparatus 600 of the present embodiment includes: a first acquisition unit 601, a second acquisition unit 602, a confidence determination unit 603, a sample generation unit 604, and a first model training unit 605.
A first obtaining unit 601 configured to obtain a first training sample set and a second training sample set. The first training sample set comprises first sample data and corresponding first labeling intents, and the second training sample set comprises second sample data and corresponding second labeling intents.
A second obtaining unit 602 configured to obtain the trained first intention recognition model and a second intention recognition model to be trained.
A confidence determining unit 603 configured to predict the first sample data using the first intention recognition model, and determine a confidence corresponding to each prediction intention;
the sample generating unit 604 is configured to determine a third training sample set according to the first annotation intention, the confidence degree corresponding to each prediction intention, and the second sample data and the corresponding second annotation intention.
A first model training unit 605 configured to train a second intent recognition model based on the third set of training samples.
In some optional implementations of this embodiment, the apparatus 600 may further include, not shown in fig. 6: a sample processing unit and a second model training unit.
And the sample processing unit is configured to process the second training sample set according to the second sample data corresponding to each second labeling intention.
And the second model training unit is configured to train the initial intention recognition model by using the processed second training sample set to obtain the first intention recognition model.
In some optional implementations of this embodiment, the sample processing unit may further include one or more of the following components not shown in fig. 6: the system comprises a subset determining module, a common sample determining module, a judging module and an intention modifying module.
The subset determining module is configured to select a first training sample subset and a second training sample subset from a second training sample set, wherein second labeling intents corresponding to the first training sample subset and the second training sample subset are different, and the quantity of second sample data in the first training sample subset is greater than that of the second sample data in the second training sample subset;
a common sample determination module configured to determine a number of common sample data of the first subset of training samples and the second subset of training samples;
the judging module is configured to determine whether a preset condition is met according to the number of the common sample data and the number of second sample data in the second training sample subset;
and the intention modification module is configured to modify a second labeling intention corresponding to the second training sample subset into a second labeling intention corresponding to the first training sample subset in response to the preset condition being met.
In some optional implementations of this embodiment, the determining module is further configured to: determining the ratio of the number of the common sample data to the number of the second sample data in the second training sample subset; in response to determining that the number of second sample data in the second subset of training samples is less than a first preset number threshold and the ratio is greater than a first preset proportion threshold, or that the ratio is greater than a second preset proportion threshold, determining that a preset condition is satisfied.
In some optional implementations of this embodiment, the sample processing unit may further include a deletion module, not shown in fig. 6, configured to delete the subset of training samples whose number of second sample data is smaller than the second preset number threshold.
In some optional implementations of this embodiment, the sample generating unit may further include one or more elements not shown in fig. 6: the device comprises a similar intention determining module, a sample data selecting module and a sample generating module.
And the similarity intention determining module is configured to determine a second annotation intention which is similar to the first annotation intention from the second training sample set according to the first annotation intention and the confidence degrees corresponding to the prediction intentions.
And the sample data selecting module is configured to select partial second sample data from the second sample data corresponding to the determined second labeling intention.
And the sample generation module is configured to determine a third training sample set according to the selected second sample data and the first training sample set.
In some optional implementations of this embodiment, the similar intent determination module is further configured to: for each first annotation intention, sorting the prediction intents in a high-to-low order according to the confidence degrees of the prediction intents of the first sample data corresponding to the first annotation intention; and regarding a second labeling intention related to the first preset number of prediction intents in the sequence in the second training sample set as a second labeling intention similar to the first labeling intention.
In some optional implementations of this embodiment, the sample data selecting module is further configured to: and for each determined second labeling intention, selecting second sample data from second sample data corresponding to the second labeling intention according to the ratio of the confidence degree corresponding to the prediction intention related to the second labeling intention to the sum of the confidence degrees corresponding to the prediction intents.
In some optional implementations of this embodiment, the sample generation module is further configured to: modifying the second labeling intention of the selected second sample data into a similar first labeling intention; and determining a third training sample set according to the marking intention corresponding to the modified second sample data and the first training sample set.
It should be understood that units 601 to 605 recited in the apparatus 600 for training a model correspond to respective steps in the method described with reference to fig. 2. Thus, the operations and features described above for the method for training a model are equally applicable to the apparatus 600 and the units contained therein and will not be described in detail here.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 7, a block diagram of an electronic device performing a method for training a model according to an embodiment of the present application is shown. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 7, the electronic apparatus includes: one or more processors 701, a memory 702, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 7, one processor 701 is taken as an example.
The memory 702 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the methods provided herein for training a model. A non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the methods provided herein for training a model.
The memory 702, as a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the method for training a model (e.g., the first acquisition unit 601, the second acquisition unit 602, the confidence determination unit 603, the sample generation unit 604, and the first model training unit 605 shown in fig. 6) in the embodiments of the present application. The processor 701 executes various functional applications of the server and data processing by executing non-transitory software programs, instructions, and modules stored in the memory 702, that is, implements the method for training a model in the above method embodiment.
The memory 702 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of an electronic device that performs training of the model, and the like. Further, the memory 702 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 702 may optionally include memory located remotely from processor 701, which may be connected via a network to an electronic device executing software for training models. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device performing the method for training a model may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected by a bus or other means, and fig. 7 illustrates an example of a connection by a bus.
The input device 703 may receive input numeric or character information and generate key signal inputs related to performing user settings and function control of the electronic apparatus used to train the model, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer stick, one or more mouse buttons, a track ball, a joystick, or other input devices. The output devices 704 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
According to the technical scheme of the embodiment of the application, historical data used for establishing the man-machine conversation robot can be fully utilized, the cost of the newly-built man-machine conversation robot is reduced, and the intention recognition effect of the newly-built man-machine conversation robot is improved under the condition of a small number of labeled samples.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (20)
1. A method for training a model, comprising:
acquiring a first training sample set and a second training sample set, wherein the first training sample set comprises first sample data and a corresponding first labeling intention, and the second training sample set comprises second sample data and a corresponding second labeling intention;
acquiring a trained first intention recognition model and a second intention recognition model to be trained;
predicting the first sample data by using the first intention recognition model, and determining confidence degrees corresponding to all prediction intents;
determining a third training sample set according to the first labeling intention, the confidence degrees corresponding to the prediction intents, second sample data and the corresponding second labeling intention;
training the second intent recognition model according to the third set of training samples.
2. The method of claim 1, wherein the method further comprises:
processing the second training sample set according to second sample data corresponding to each second labeling intention;
and training an initial intention recognition model by utilizing the processed second training sample set to obtain the first intention recognition model.
3. The method according to claim 2, wherein the processing the second training sample set according to the second sample data corresponding to each second labeling intention includes:
selecting a first training sample subset and a second training sample subset from the second training sample set, wherein second labeling intents corresponding to the first training sample subset and the second training sample subset are different, and the quantity of second sample data in the first training sample subset is greater than that of second sample data in the second training sample subset;
determining a number of common sample data of the first subset of training samples and the second subset of training samples;
determining whether a preset condition is met according to the number of the common sample data and the number of second sample data in the second training sample subset;
and in response to the preset condition being met, modifying the second labeling intention corresponding to the second training sample subset into the second labeling intention corresponding to the first training sample subset.
4. The method of claim 3, wherein said determining whether a preset condition is met according to the number of common sample data, the number of samples in the second subset of training samples, comprises:
determining a ratio of the number of the common sample data to the number of second sample data in the second subset of training samples;
in response to determining that the number of second sample data in the second subset of training samples is less than a first preset number threshold and the ratio is greater than a first preset proportion threshold, or that the ratio is greater than a second preset proportion threshold, determining that the preset condition is met.
5. The method according to claim 2, wherein the processing the second training sample set according to the second sample data corresponding to each second labeling intention includes:
and deleting the training sample subset of which the number of the second sample data is less than a second preset number threshold.
6. The method of claim 1, wherein determining a third set of training samples according to the first annotation intention, the confidence degree corresponding to each prediction intention, and the second sample data and the corresponding second annotation intention comprises:
determining a second labeling intention similar to the first labeling intention from the second training sample set according to the first labeling intention and the confidence degrees corresponding to the prediction intents;
selecting part of second sample data from the second sample data corresponding to the determined second labeling intention;
and determining the third training sample set according to the selected second sample data and the first training sample set.
7. The method of claim 6, wherein the determining, from the second training sample set, a second annotation intent that is similar to the annotation intent according to the first annotation intent and the confidence level corresponding to each predicted intent comprises:
for each first labeling intention, sorting the prediction intents in a high-to-low order according to the confidence degrees of the prediction intents of the first sample data corresponding to the first labeling intention;
and taking the second labeling intention related to the first preset number of prediction intents in the sequence in the second training sample set as a second labeling intention similar to the first labeling intention.
8. The method of claim 6, wherein said selecting a portion of second sample data from the second sample data corresponding to the determined second annotation intent comprises:
and for each determined second labeling intention, selecting second sample data from second sample data corresponding to the second labeling intention according to the ratio of the confidence degree corresponding to the prediction intention related to the second labeling intention to the sum of the confidence degrees corresponding to the prediction intents.
9. The method according to claim 6, wherein said determining the third set of training samples from the selected second sample data and the first set of training samples comprises:
modifying the second labeling intention of the selected second sample data into a similar first labeling intention;
and determining the third training sample set according to the marking intention corresponding to the modified second sample data and the first training sample set.
10. An apparatus for training a model, comprising:
a first obtaining unit configured to obtain a first training sample set and a second training sample set, wherein the first training sample set comprises first sample data and a corresponding first labeling intention, and the second training sample set comprises second sample data and a corresponding second labeling intention;
a second acquisition unit configured to acquire the trained first intention recognition model and a second intention recognition model to be trained;
a confidence degree determining unit configured to predict the first sample data by using the first intention recognition model, and determine a confidence degree corresponding to each prediction intention;
the sample generation unit is configured to determine a third training sample set according to the first annotation intention, the confidence degrees corresponding to the prediction intents, second sample data and corresponding second annotation intention;
a first model training unit configured to train the second intent recognition model according to the third set of training samples.
11. The apparatus of claim 10, wherein the apparatus further comprises:
a sample processing unit configured to process the second training sample set according to second sample data corresponding to each of the second annotation intents;
and the second model training unit is configured to train the initial intention recognition model by using the processed second training sample set to obtain the first intention recognition model.
12. The apparatus of claim 11, wherein the sample processing unit comprises:
a subset determining module configured to select a first training sample subset and a second training sample subset from the second training sample set, where the first training sample subset and the second training sample subset correspond to different second labeling intents, and a quantity of second sample data in the first training sample subset is greater than a quantity of second sample data in the second training sample subset;
a common sample determination module configured to determine a number of common sample data of the first subset of training samples and the second subset of training samples;
a judging module configured to determine whether a preset condition is met according to the number of the common sample data and the number of second sample data in the second training sample subset;
and the intention modification module is configured to modify a second labeling intention corresponding to the second training sample subset into a second labeling intention corresponding to the first training sample subset in response to the preset condition being met.
13. The apparatus of claim 12, wherein the determining module is further configured to:
determining a ratio of the number of the common sample data to the number of second sample data in the second subset of training samples;
in response to determining that the number of second sample data in the second subset of training samples is less than a first preset number threshold and the ratio is greater than a first preset proportion threshold, or that the ratio is greater than a second preset proportion threshold, determining that the preset condition is met.
14. The apparatus of claim 12, wherein the sample processing unit comprises:
a deletion module configured to delete the subset of training samples for which the number of the second sample data is less than a second preset number threshold.
15. The apparatus of claim 10, wherein the sample generation unit comprises:
a similarity intention determining module configured to determine a second labeling intention similar to the first labeling intention from the second training sample set according to the first labeling intention and the confidence degrees corresponding to the prediction intentions;
the sample data selecting module is configured to select partial second sample data from second sample data corresponding to the determined second labeling intention;
a sample generation module configured to determine the third training sample set according to the selected second sample data and the first training sample set.
16. The apparatus of claim 15, wherein the similar intent determination module is further configured to:
for each first labeling intention, sorting the prediction intents in a high-to-low order according to the confidence degrees of the prediction intents of the first sample data corresponding to the first labeling intention;
and taking the second labeling intention related to the first preset number of prediction intents in the sequence in the second training sample set as a second labeling intention similar to the first labeling intention.
17. The apparatus of claim 15, wherein the sample data selection module is further configured to:
and for each determined second labeling intention, selecting second sample data from second sample data corresponding to the second labeling intention according to the ratio of the confidence degree corresponding to the prediction intention related to the second labeling intention to the sum of the confidence degrees corresponding to the prediction intents.
18. The apparatus of claim 15, wherein the sample generation module is further configured to:
modifying the second labeling intention of the selected second sample data into a similar first labeling intention;
and determining the third training sample set according to the marking intention corresponding to the modified second sample data and the first training sample set.
19. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.
20. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010524463.3A CN111680517B (en) | 2020-06-10 | 2020-06-10 | Method, apparatus, device and storage medium for training model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010524463.3A CN111680517B (en) | 2020-06-10 | 2020-06-10 | Method, apparatus, device and storage medium for training model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111680517A true CN111680517A (en) | 2020-09-18 |
| CN111680517B CN111680517B (en) | 2023-05-16 |
Family
ID=72454836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010524463.3A Active CN111680517B (en) | 2020-06-10 | 2020-06-10 | Method, apparatus, device and storage medium for training model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111680517B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112257458A (en) * | 2020-10-21 | 2021-01-22 | 阳光保险集团股份有限公司 | Intention recognition model training method, intention recognition method, device and equipment |
| CN112529624A (en) * | 2020-12-15 | 2021-03-19 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating business prediction model |
| CN112541739A (en) * | 2020-12-15 | 2021-03-23 | 平安科技（深圳）有限公司 | Method, device, equipment and medium for testing question-answer intention classification model |
| CN112560992A (en) * | 2020-12-25 | 2021-03-26 | 北京百度网讯科技有限公司 | Method and device for optimizing image classification model, electronic equipment and storage medium |
| CN112669816A (en) * | 2020-12-24 | 2021-04-16 | 北京有竹居网络技术有限公司 | Model training method, speech recognition method, device, medium and equipment |
| CN112966108A (en) * | 2021-03-08 | 2021-06-15 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for detecting data and training classification model |
| CN113569546A (en) * | 2021-06-16 | 2021-10-29 | 上海淇玥信息技术有限公司 | Intention labeling method and device and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920622A (en) * | 2018-06-29 | 2018-11-30 | 北京奇艺世纪科技有限公司 | A kind of training method of intention assessment, training device and identification device |
| CN109063221A (en) * | 2018-11-02 | 2018-12-21 | 北京百度网讯科技有限公司 | Query intention recognition methods and device based on mixed strategy |
| CN109086814A (en) * | 2018-07-23 | 2018-12-25 | 腾讯科技（深圳）有限公司 | A kind of data processing method, device and the network equipment |
| CN109522556A (en) * | 2018-11-16 | 2019-03-26 | 北京九狐时代智能科技有限公司 | A kind of intension recognizing method and device |
| CN110457449A (en) * | 2019-07-05 | 2019-11-15 | 阿里巴巴集团控股有限公司 | Method, apparatus, equipment and the storage medium of on-line training model |
| US20200065384A1 (en) * | 2018-08-26 | 2020-02-27 | CloudMinds Technology, Inc. | Method and System for Intent Classification |
| CN110990576A (en) * | 2019-12-24 | 2020-04-10 | 用友网络科技股份有限公司 | Intention classification method based on active learning, computer device and storage medium |
| CN111143561A (en) * | 2019-12-26 | 2020-05-12 | 北京百度网讯科技有限公司 | Intention recognition model training method and device and electronic equipment |
-
2020
- 2020-06-10 CN CN202010524463.3A patent/CN111680517B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920622A (en) * | 2018-06-29 | 2018-11-30 | 北京奇艺世纪科技有限公司 | A kind of training method of intention assessment, training device and identification device |
| CN109086814A (en) * | 2018-07-23 | 2018-12-25 | 腾讯科技（深圳）有限公司 | A kind of data processing method, device and the network equipment |
| US20200065384A1 (en) * | 2018-08-26 | 2020-02-27 | CloudMinds Technology, Inc. | Method and System for Intent Classification |
| CN109063221A (en) * | 2018-11-02 | 2018-12-21 | 北京百度网讯科技有限公司 | Query intention recognition methods and device based on mixed strategy |
| CN109522556A (en) * | 2018-11-16 | 2019-03-26 | 北京九狐时代智能科技有限公司 | A kind of intension recognizing method and device |
| CN110457449A (en) * | 2019-07-05 | 2019-11-15 | 阿里巴巴集团控股有限公司 | Method, apparatus, equipment and the storage medium of on-line training model |
| CN110990576A (en) * | 2019-12-24 | 2020-04-10 | 用友网络科技股份有限公司 | Intention classification method based on active learning, computer device and storage medium |
| CN111143561A (en) * | 2019-12-26 | 2020-05-12 | 北京百度网讯科技有限公司 | Intention recognition model training method and device and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| MATEUSZ BUDNIK等: ""Rethinking deep active learning:Using unlabeled data at model training"" * |
| 付博;陈毅恒;邵艳秋;刘挺;: ""基于用户自然标注的微博文本的消费意图识别"" * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112257458A (en) * | 2020-10-21 | 2021-01-22 | 阳光保险集团股份有限公司 | Intention recognition model training method, intention recognition method, device and equipment |
| CN112529624A (en) * | 2020-12-15 | 2021-03-19 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating business prediction model |
| CN112541739A (en) * | 2020-12-15 | 2021-03-23 | 平安科技（深圳）有限公司 | Method, device, equipment and medium for testing question-answer intention classification model |
| WO2022126987A1 (en) * | 2020-12-15 | 2022-06-23 | 平安科技（深圳）有限公司 | Test method and apparatus for question-and-answer intention classification model, device and medium |
| CN112529624B (en) * | 2020-12-15 | 2024-01-09 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating business prediction model |
| CN112669816A (en) * | 2020-12-24 | 2021-04-16 | 北京有竹居网络技术有限公司 | Model training method, speech recognition method, device, medium and equipment |
| CN112669816B (en) * | 2020-12-24 | 2023-06-02 | 北京有竹居网络技术有限公司 | Model training method, voice recognition method, device, medium and equipment |
| CN112560992A (en) * | 2020-12-25 | 2021-03-26 | 北京百度网讯科技有限公司 | Method and device for optimizing image classification model, electronic equipment and storage medium |
| CN112560992B (en) * | 2020-12-25 | 2023-09-01 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and storage medium for optimizing picture classification model |
| CN112966108A (en) * | 2021-03-08 | 2021-06-15 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for detecting data and training classification model |
| CN112966108B (en) * | 2021-03-08 | 2024-03-12 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for detecting data and training classification model |
| CN113569546A (en) * | 2021-06-16 | 2021-10-29 | 上海淇玥信息技术有限公司 | Intention labeling method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111680517B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428008B (en) | Method, apparatus, device and storage medium for training a model | |
| CN111680517B (en) | Method, apparatus, device and storage medium for training model | |
| CN111639710A (en) | Image recognition model training method, device, equipment and storage medium | |
| CN112036509A (en) | Method and apparatus for training image recognition models | |
| CN112507735B (en) | Training method and device of machine translation model and electronic equipment | |
| CN111708922A (en) | Model generation method and device for representing heterogeneous graph nodes | |
| CN111104514A (en) | Method and device for training document label model | |
| CN111078878B (en) | Text processing method, device, equipment and computer readable storage medium | |
| CN111522967A (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN112559870B (en) | Multi-model fusion method, device, electronic equipment and storage medium | |
| CN111667056A (en) | Method and apparatus for searching model structure | |
| CN111460135B (en) | Method and device for generating text abstract | |
| CN111339759A (en) | Method and device for training field element recognition model and electronic equipment | |
| CN111582477A (en) | Training method and device of neural network model | |
| CN111241838B (en) | Semantic relation processing method, device and equipment for text entity | |
| CN110717340A (en) | Recommendation method and device, electronic equipment and storage medium | |
| CN111522944A (en) | Method, apparatus, device and storage medium for outputting information | |
| CN111783013A (en) | Comment information publishing method, device, equipment and computer-readable storage medium | |
| CN111311309A (en) | User satisfaction determining method, device, equipment and medium | |
| CN111666771A (en) | Semantic label extraction device, electronic equipment and readable storage medium of document | |
| CN112232089B (en) | Pre-training method, device and storage medium of semantic representation model | |
| CN114547244A (en) | Method and apparatus for determining information | |
| CN112580723B (en) | Multi-model fusion method, device, electronic equipment and storage medium | |
| CN112270169B (en) | Method and device for predicting dialogue roles, electronic equipment and storage medium | |
| CN111325006B (en) | Information interaction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |