CN112632279B - Method and related device for determining user tag - Google Patents
Method and related device for determining user tag Download PDFInfo
- Publication number
- CN112632279B CN112632279B CN202011521477.6A CN202011521477A CN112632279B CN 112632279 B CN112632279 B CN 112632279B CN 202011521477 A CN202011521477 A CN 202011521477A CN 112632279 B CN112632279 B CN 112632279B
- Authority
- CN
- China
- Prior art keywords
- target user
- fine
- grained
- user
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000003058 natural language processing Methods 0.000 claims abstract description 38
- 238000005065 mining Methods 0.000 claims description 58
- 238000012545 processing Methods 0.000 claims description 21
- 238000012216 screening Methods 0.000 claims description 9
- 230000003542 behavioural effect Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 claims 6
- 230000006399 behavior Effects 0.000 description 12
- 238000013473 artificial intelligence Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000005457 optimization Methods 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
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000005354 coacervation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development 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
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
The application discloses a method and a related device for determining a user tag, wherein the method comprises the following steps: performing natural language processing on the input information of the target user to obtain fine-grained slot position information in the input information; and deducing the fine granularity label of the target user through the fine granularity slot position information. The input information of the user is related input content conforming to the personalized habit of the user, and the fine granularity slot information of the input information can finely represent personalized label information of the user; the user label can be obtained by analyzing the fine-granularity slot position information by excavating the fine-granularity slot position information in the input information of the user; the method for determining the user tag is convenient, and the determined user tag is a fine-grained tag, so that the personalized performance of the artificial intelligent user is improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and a related device for determining a user tag.
Background
With the rapid development of artificial intelligence, various artificial intelligence products are continuously introduced, and people are full of imagination and expectations for artificial intelligence. One important aspect in artificial intelligence is user personalization; that is, when the artificial intelligence product faces different users, it is able to provide personalized artificial intelligence services according to tags of different users. Based on this, determining the user's tag has a tremendous role in achieving artificial intelligence user personalization, especially for fine-grained tags of the user.
Currently, demographic attribute tags, interest tags, behavior tags, and the like of users are generally determined by social data, attribute data, behavior data, and the like of the users. However, population attribute labels, interest labels and behavior labels of the users determined in the mode are coarse granularity labels; that is, the existing method cannot or hardly determine the fine-grained label of the user, and cannot meet the requirement of determining the fine-grained label of the user, thereby affecting the personalized performance of the artificial intelligence user.
Disclosure of Invention
In view of the above, the present application provides a method and related device for determining a user tag, where the method for determining a user tag is relatively convenient, and the determined user tag is a fine-grained tag, so as to facilitate improving the personalized performance of an artificial intelligence user.
In a first aspect, an embodiment of the present application provides a method for determining a user tag, where the method includes:
performing natural language processing on input information of a target user;
acquiring fine-grained slot position information in the input information;
and deducing the fine granularity label of the target user based on the fine granularity slot position information.
Optionally, the natural language processing is performed on the input information of the target user, specifically:
Performing natural language processing on the input information by using a slot mining algorithm and an intention classifier; the slot digging algorithm comprises a slot digging template or a slot digging model.
Optionally, the method further comprises:
Determining a target user cluster to which the target user belongs;
Based on the input information of the users in the target user cluster and the corresponding fine-grained slot position information, adjusting the slot position mining algorithm to obtain a new slot position mining algorithm;
The method comprises the following steps of performing natural language processing on input information by using a slot mining algorithm and an intention classifier, wherein the natural language processing is specifically as follows:
and carrying out natural language processing on the input information by utilizing the new slot mining algorithm and the intention classifier.
Optionally, the method further comprises:
Deducing a person-set label of the target user based on the fine-grained slot position information;
Screening fine-granularity labels matched with the manual label from the fine-granularity labels;
and determining the target fine granularity label of the target user.
Optionally, the method further comprises:
Determining a target user cluster to which the target user belongs;
If the target fine-grained labels of the preset number of users in the target user cluster comprise first target fine-grained labels, determining the first target fine-grained labels as target fine-grained labels of the users in the target user cluster;
The preset number is smaller than the number of users in the target user cluster.
Optionally, the determining the target user cluster to which the target user belongs specifically includes:
Determining a target user cluster to which the target user belongs based on the related data of the target user and the related data of other users; the related data includes social data, attribute data, and/or behavioral data.
Optionally, the determining, based on the related data of the target user and other users, a target user cluster to which the target user belongs includes:
Based on the related data of the target user and the related data of the other users, obtaining the similarity among the users;
constructing a user graph network based on the similarity among the users;
and determining a target user cluster to which the target user belongs based on the user graph network.
In a second aspect, an embodiment of the present application provides an apparatus for determining a user tag, where the apparatus includes:
The processing unit is used for carrying out natural language processing on the input information of the target user;
the obtaining unit is used for obtaining fine-grained slot position information in the input information;
and the first deducing unit is used for deducing the fine granularity label of the target user based on the fine granularity slot position information.
Optionally, the processing unit is specifically configured to:
Performing natural language processing on the input information by using a slot mining algorithm and an intention classifier; the slot digging algorithm comprises a slot digging template or a slot digging model.
Optionally, the apparatus further includes:
a first determining unit, configured to determine a target user cluster to which the target user belongs;
The adjusting unit is used for adjusting the slot mining algorithm to obtain a new slot mining algorithm based on the input information of the users in the target user cluster and the corresponding fine-grained slot information;
Wherein, the processing unit is specifically configured to:
And carrying out natural language processing on the input information by using a new slot mining algorithm and the intention classifier.
Optionally, the apparatus further includes:
the second deducing unit is used for deducing the personal setting label of the target user based on the fine-granularity slot position information;
The screening unit is used for screening the fine-granularity labels matched with the manual label from the fine-granularity labels;
And the second determining unit is used for determining the target fine granularity label of the target user.
Optionally, the apparatus further includes:
a first determining unit, configured to determine a target user cluster to which the target user belongs;
A third determining unit, configured to determine, if target fine-grained labels of a preset number of users in the target user cluster include first target fine-grained labels, the first target fine-grained labels as target fine-grained labels of users in the target user cluster;
The preset number is smaller than the number of users in the target user cluster.
Optionally, the first determining unit is specifically configured to:
Determining a target user cluster to which the target user belongs based on the related data of the target user and the related data of other users; the related data includes social data, attribute data, and/or behavioral data.
Optionally, the first determining unit includes:
An obtaining subunit, configured to obtain a similarity between each user based on the related data of the target user and the related data of the other users;
A construction subunit, configured to construct a user graph network based on the similarity between the users;
And the determining subunit is used for determining a target user cluster to which the target user belongs based on the user graph network.
In a third aspect, embodiments of the present application provide an apparatus for determining a user tag, the apparatus comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:
performing natural language processing on input information of a target user;
acquiring fine-grained slot position information in the input information;
and deducing the fine granularity label of the target user based on the fine granularity slot position information.
In a fourth aspect, embodiments of the present application provide a machine-readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform a method of determining a user tag as in any of the first aspects above.
Compared with the prior art, the application has at least the following advantages:
By adopting the technical scheme of the embodiment of the application, the input information of the target user is subjected to natural language processing to obtain fine-grained slot position information in the input information; and deducing the fine granularity label of the target user through the fine granularity slot position information. The input information of the user is related input content conforming to the personalized habit of the user, and the fine granularity slot information of the input information can finely represent personalized label information of the user; the user label can be obtained by analyzing the fine-granularity slot position information by excavating the fine-granularity slot position information in the input information of the user; the method for determining the user tag is convenient, and the determined user tag is a fine-grained tag, so that the personalized performance of the artificial intelligent user is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a system frame related to an application scenario in an embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for determining a user tag according to an embodiment of the present application;
fig. 3 is a schematic diagram of a user graph network according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of an apparatus for determining a user tag according to an embodiment of the present application;
FIG. 5 is a schematic structural diagram of an apparatus for determining a user tag according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
In order to make the present application better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
At present, demographic attribute tags, interest tags, behavior tags and the like of users are generally determined by using social data, attribute data, behavior data and the like of the users. However, population attribute labels, interest labels and behavior labels of the users determined in the mode are coarse granularity labels, and in order to better realize the individuation of the artificial intelligence users, fine granularity labels of the users need to be determined; that is, existing approaches fail to or have difficulty determining fine-grained labels for users, thereby affecting the performance of the artificial intelligence user personalization.
In order to solve the problem, in the embodiment of the application, natural language processing is carried out on the input information of the target user to obtain fine-grained slot position information in the input information; and deducing the fine granularity label of the target user through the fine granularity slot position information. The input information of the user is related input content conforming to the personalized habit of the user, and the fine granularity slot information of the input information can finely represent personalized label information of the user; the user label can be obtained by analyzing the fine-granularity slot position information by excavating the fine-granularity slot position information in the input information of the user; the method for determining the user tag is convenient, and the determined user tag is a fine-grained tag, so that the personalized performance of the artificial intelligent user is improved.
For example, one of the scenarios of the embodiment of the present application may be applied to the scenario shown in fig. 1, which includes the user terminal 101 and the processor 102. The target user obtains input information through input operation of the user terminal 101, the user terminal 101 sends the input information of the target user to the processor 102, and the processor 102 obtains the fine-grained label of the target user by adopting the embodiment of the application.
It will be appreciated that in the above application scenario, although the description of the actions of the embodiments of the present application is performed by the server 101; however, the present application is not limited to the execution subject, and the operations disclosed in the embodiments of the present application may be executed.
It will be appreciated that the above scenario is merely an example of one scenario provided by embodiments of the present application, and embodiments of the present application are not limited to this scenario.
The following describes in detail, by way of example, specific implementation manners of a method and related apparatus for determining a user tag according to an embodiment of the present application with reference to the accompanying drawings.
Exemplary method
Referring to fig. 2, a flowchart of a method for determining a user tag according to an embodiment of the present application is shown. In this embodiment, the method may include, for example, the steps of:
Step 201: and carrying out natural language processing on the input information of the target user.
Because population attribute tags, interest tags and behavior tags of the user, which are determined by social data, attribute data and behavior data of the user, are coarse-grained tags, the requirements for determining fine-grained tags of the user cannot be met; in the method, the acquisition and collection of social data, attribute data and behavior data of the user are complex and difficult, and the method for determining the labels of the users by different types of data is inconsistent. In the embodiment of the application, the input information of the user is taken into consideration as the related input content conforming to the personalized habit of the user, so that the input information is easy to acquire and collect; and the content of the personalized tag information of the user can be mined from the input information of the user by adopting a natural language processing mode. Therefore, taking any user as a target user, firstly, carrying out natural language processing on the input information of the target user; that is, step 201 is performed.
In the embodiment of the present application, when step 201 is specifically implemented, the purpose of performing natural language processing on the input information of the target user is: mining the content of the personalized tag information of the characterization user from the input information of the target user; that is, the content corresponding to each slot in the input information of the target user is mined. Therefore, it is necessary to use a slot mining algorithm when performing natural language processing on input information of a target user, wherein the slot mining algorithm is divided into a template-based slot mining algorithm (slot mining template) and a model-based slot mining algorithm (slot mining model); that is, the slot mining algorithm may be either a slot mining template or a slot mining model. In addition, the intention of the input information of the target user needs to be analyzed, so that the accuracy of mining the content representing the personalized tag information of the user from the input information of the user by using a slot mining algorithm is improved, and an intention classifier needs to be used when the input information of the target user is subjected to natural language processing. Thus, in an alternative implementation manner of the embodiment of the present application, the step 201 may be, for example, specifically: performing natural language processing on the input information by using a slot mining algorithm and an intention classifier; the slot digging algorithm comprises a slot digging template or a slot digging model.
As an example, the slot mining algorithm may be a conditional random field (english: conditional random field algorithm, abbreviation: CRF) model or a Long Short Term Memory-conditional random field (english: long Short-Term Memory-conditional random field algorithm, abbreviation: LSTM-CRF) model, or the like; the intention classifier may be a text convolutional neural network (english: text Convolutional Neural Networks, abbreviation: textCNN) model, a support vector machine (english: support vector machines, abbreviation: SVM) model, or a naive bayes model (english: naive Bayes model, abbreviation: NBM) or the like.
Step 202: and obtaining fine-grained slot position information in the input information.
In the embodiment of the present application, in step 201, natural language processing is performed on input information of a target user, after content representing user personalized tag information is mined from the input information of the user, the content representing the user personalized tag information obtained by mining can be used as fine-granularity slot information; namely, fine-grained slot information in the input information of the target user is obtained.
As an example, the input information of the target user is "i'm research into XX university", and the input information is subjected to natural language processing by using a slot mining algorithm and an intention classifier, so that fine-grained slot information in the input information is "research", "XX university". As another example, the input information of the target user is 'I write work', and in the mode, the fine-granularity slot information in the input information is 'write work'. As still another example, the input information of the target user is "i am a question to i am by i am, and in the above manner, the fine-grained slot information in the input information is" i am "or" question ".
In addition, in the embodiment of the application, the slot digging algorithm comprises a slot digging template or a slot digging model, wherein the slot digging template is substantially preset, and the slot digging model is substantially pre-trained; that is, fine-grained slot information obtained by slot mining of input information using a slot mining algorithm is not exhaustive; therefore, a large amount of input information and corresponding fine-grained slot information needs to be obtained, and the slot mining algorithm is adjusted to optimize the slot mining algorithm, so that a new slot mining algorithm is adopted when step 201 is implemented, so that fine-grained slot information in the input information of the target user is fully mined.
The data size of the fine-grained slot position information in the input information of the target user is not large, and the input information of other users and the corresponding fine-grained slot position information are required to be obtained; however, the input information of any other user and the corresponding fine-grained slot position information can not be used for adjusting the slot position mining algorithm to optimize the slot position mining algorithm, so that the adjustment and optimization engineering quantity of the slot position mining algorithm is huge easily. In consideration of different user clustering clusters obtained by different user clustering, the input information of the user in the target user clustering cluster to which the target user belongs and the corresponding fine-grained slot information can be utilized to adjust the slot mining algorithm to optimize the slot mining algorithm, so that the adjustment and optimization engineering quantity of the slot mining algorithm can be greatly reduced, and the adjustment and optimization of the slot mining algorithm through the correlation among the fine-grained slot information in the input information of the user in the user clustering cluster is greatly avoided. That is, in an alternative implementation manner of the embodiment of the present application, for example, the following steps may be further included:
Step A: and determining a target user cluster to which the target user belongs.
The social data, attribute data and/or behavior data of any user can be obtained, and on the basis, the target user and other users can be clustered through the social data, attribute data and/or behavior data of the target user and other users, so that a target user cluster to which the target user belongs is determined. Thus, in an alternative implementation manner of the embodiment of the present application, the step a may be, for example, specifically: determining a target user cluster to which the target user belongs based on the related data of the target user and the related data of other users; the related data includes social data, attribute data, and/or behavioral data.
On the basis of the above description, when the step A is implemented, firstly, the similarity between the users can be calculated through social data, attribute data and/or behavior data of the target users and other users so as to represent the aggregation degree between the users; then, according to the similarity between the users, establishing an edge relationship between the users to construct a user graph network, for example, a schematic diagram of a user graph network as shown in fig. 3; and finally, carrying out graph network clustering on the basis of the user graph network, thereby determining a target user cluster to which the target user belongs. The algorithm of graph network clustering can be KERNIGHAN-Lin algorithm, spectral analysis method, coacervation method or Newman algorithm. Thus, in an alternative implementation of the embodiment of the present application, the step a may include, for example, the following steps:
Step A1: and obtaining the similarity among the users based on the related data of the target user and the related data of other users.
Step A2: and constructing a user graph network based on the similarity among the users.
Step A3: and determining a target user cluster to which the target user belongs based on the user graph network.
And (B) step (B): and adjusting the slot mining algorithm to obtain a new slot mining algorithm based on the input information of the users in the target user cluster and the corresponding fine-grained slot information.
The specific implementation manners of obtaining the fine-grained slot information in the input information in the target user cluster by referring to the steps 201 to 202 may be adopted for the input information of the user and the corresponding fine-grained slot information in the target user cluster.
Correspondingly, after performing steps a to B, the step 201 may be, for example, specifically: and carrying out natural language processing on the input information by using a new slot mining algorithm and the intention classifier.
Step 203: and deducing the fine granularity label of the target user based on the fine granularity slot position information.
In the embodiment of the present application, after the fine-grained slot information in the input information of the target user is obtained in step 202, on the basis that the fine-grained slot information characterizes the personalized tag information of the target user, the fine-grained tag of the target user may be inferred according to the fine-grained slot information. Specifically, the fine granularity slot information can be directly used as the fine granularity label of the target user, and the fine granularity label of the target user can be obtained by analyzing the fine granularity slot information.
As an example, the input information of the target user is "i'm research into XX university", the fine-grained slot information is "research", "XX university", and the fine-grained label of the target user can be inferred to be "XX university" from the fine-grained slot information.
After deducing the fine-grained label of the target user in step 203, in order to improve the accuracy of the fine-grained label of the target user, further verification of the fine-grained label of the target user is required, and only the fine-grained label of the label set by the person conforming to the target user can be determined as the target fine-grained label of the target user. Specifically, firstly, the person-set label of the target user can be deduced through fine-grained slot position information in the input information of the target user; then judging whether the fine-grained label of the target user is matched with the human-set label of the target user; and finally, determining that a person matched with the target user sets a label to obtain a fine-granularity label serving as the target fine-granularity label of the target user. The method enables the target fine-grained labels of the target users to be more accurate than the fine-grained labels. Thus, in an alternative implementation of the embodiment of the present application, the following steps may be further included, for example:
Step C: and deducing the personnel set label of the target user based on the fine-granularity slot position information.
Step D: and screening the fine-granularity labels matched with the manual label from the fine-granularity labels.
Step E: and determining the target fine granularity label of the target user.
As an example, the input information of the target user is "i am writing", "i am a question is arranged for i by i am director", the fine-grained slot information is "writing", "i am director", "question", and it can be inferred from the fine-grained slot information that the person of the target user sets the label as "study". If the fine granularity label of the target user is 'XX university', and the fine granularity label 'XX university' is matched with the manual label 'research student', the target fine granularity label of the target user is 'XX university'.
In addition, in the embodiment of the present application, based on the determination of the target user cluster to which the target user belongs, any user in the target user cluster may determine the target fine-grained label by using the specific embodiment; on the basis, when the target fine-grained labels of part of users in the target user cluster all comprise first target fine-grained labels, the users in the target user cluster can be considered to all have the first target fine-grained labels, namely; copying the first target fine-granularity tag propagation to users in a target user cluster; wherein, the partial user quantity (preset quantity) in the target user cluster is preset by the user quantity in the target user cluster. Thus, in an alternative implementation of the embodiment of the present application, the following steps may be further included, for example:
step F: and determining a target user cluster to which the target user belongs.
The detailed description of step F is referred to the detailed description of step a, and is not repeated here.
Step G: if the target fine granularity labels of the preset number of users in the target user cluster comprise first target fine granularity labels, determining the first target fine granularity labels as the target fine granularity labels of the users in the target user cluster.
The preset number is smaller than the number of users in the target user cluster.
It should be noted that, by adopting the above embodiment, the same situation of the fine granularity labels among different users in the user cluster is counted, and the same fine granularity label is propagated in the user cluster, so that the problem that the determined fine granularity label is less due to the fact that the fine granularity label is inferred only by adopting the input information when the input information of the user in the user cluster is less can be solved.
Through the various implementation manners provided by the embodiment, natural language processing is performed on the input information of the target user, and fine-grained slot position information in the input information is obtained; and deducing the fine granularity label of the target user through the fine granularity slot position information. The input information of the user is related input content conforming to the personalized habit of the user, and the fine granularity slot information of the input information can finely represent personalized label information of the user; the user label can be obtained by analyzing the fine-granularity slot position information by excavating the fine-granularity slot position information in the input information of the user; the method for determining the user tag is convenient, and the determined user tag is a fine-grained tag, so that the personalized performance of the artificial intelligent user is improved.
Exemplary apparatus
Referring to fig. 4, a schematic structural diagram of an apparatus for determining a user tag according to an embodiment of the present application is shown. In this embodiment, the apparatus may specifically include, for example:
A processing unit 401, configured to perform natural language processing on input information of a target user;
an obtaining unit 402, configured to obtain fine-grained slot information in the input information;
a first inference unit 403, configured to infer a fine granularity tag of the target user based on the fine granularity slot information.
In an alternative implementation manner of the embodiment of the present application, the processing unit 401 is specifically configured to:
Performing natural language processing on the input information by using a slot mining algorithm and an intention classifier; the slot digging algorithm comprises a slot digging template or a slot digging model.
In an alternative implementation manner of the embodiment of the present application, the apparatus further includes:
a first determining unit, configured to determine a target user cluster to which the target user belongs;
The adjusting unit is used for adjusting the slot mining algorithm to obtain a new slot mining algorithm based on the input information of the users in the target user cluster and the corresponding fine-grained slot information;
wherein, the processing unit 401 is specifically configured to:
And carrying out natural language processing on the input information by using a new slot mining algorithm and the intention classifier.
In an alternative implementation manner of the embodiment of the present application, the apparatus further includes:
the second deducing unit is used for deducing the personal setting label of the target user based on the fine-granularity slot position information;
The screening unit is used for screening the fine-granularity labels matched with the manual label from the fine-granularity labels;
And the second determining unit is used for determining the target fine granularity label of the target user.
In an alternative implementation manner of the embodiment of the present application, the apparatus further includes:
a first determining unit, configured to determine a target user cluster to which the target user belongs;
A third determining unit, configured to determine, if target fine-grained labels of a preset number of users in the target user cluster include first target fine-grained labels, the first target fine-grained labels as target fine-grained labels of users in the target user cluster;
The preset number is smaller than the number of users in the target user cluster.
In an optional implementation manner of the embodiment of the present application, the first determining unit is specifically configured to:
Determining a target user cluster to which the target user belongs based on the related data of the target user and the related data of other users; the related data includes social data, attribute data, and/or behavioral data.
In an optional implementation manner of the embodiment of the present application, the first determining unit includes:
An obtaining subunit, configured to obtain a similarity between each user based on the related data of the target user and the related data of the other users;
A construction subunit, configured to construct a user graph network based on the similarity between the users;
And the determining subunit is used for determining a target user cluster to which the target user belongs based on the user graph network.
Through the various implementation manners provided by the embodiment, natural language processing is performed on the input information of the target user, and fine-grained slot position information in the input information is obtained; and deducing the fine granularity label of the target user through the fine granularity slot position information. The input information of the user is related input content conforming to the personalized habit of the user, and the fine granularity slot information of the input information can finely represent personalized label information of the user; the user label can be obtained by analyzing the fine-granularity slot position information by excavating the fine-granularity slot position information in the input information of the user; the method for determining the user tag is convenient, and the determined user tag is a fine-grained tag, so that the personalized performance of the artificial intelligent user is improved.
Fig. 5 is a block diagram illustrating an apparatus 500 for determining a user tag according to an example embodiment. For example, the apparatus 500 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, or the like.
Referring to fig. 5, an apparatus 500 may include one or more of the following components: a processing component 502, a memory 504, a power supply component 506, a multimedia component 508, an audio component 510, an input/output (I/O) interface 512, a sensor component 514, and a communication component 516.
The processing component 502 generally controls overall operation of the apparatus 500, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 502 can include one or more modules that facilitate interactions between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate interaction between the multimedia component 508 and the processing component 502.
The memory 505 is configured to store various types of data to support operations at the device 500. Examples of such data include instructions for any application or method operating on the apparatus 500, contact data, phonebook data, messages, pictures, videos, and the like. The memory 504 may be implemented by any type or combination of volatile or nonvolatile 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 disk.
The power supply component 506 provides power to the various components of the device 500. The power components 506 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 500.
The multimedia component 508 includes a screen between the device 500 and the user that provides an output interface. 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 input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or sliding action, but also the duration and pressure associated with the touch or sliding operation. In some embodiments, the multimedia component 508 includes a front-facing camera and/or a rear-facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 500 is in an operational 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 focal length and optical zoom capabilities.
The audio component 510 is configured to output and/or input audio signals. For example, the audio component 510 includes a Microphone (MIC) configured to receive external audio signals when the device 500 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 504 or transmitted via the communication component 516. In some embodiments, the audio component 510 further comprises a speaker for outputting audio signals.
The I/O interface 512 provides an interface between the processing component 502 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 514 includes one or more sensors for providing status assessment of various aspects of the apparatus 500. For example, the sensor assembly 514 may detect the on/off state of the device 500, the relative positioning of the components, such as the display and keypad of the apparatus 500, the sensor assembly 514 may also detect a change in position of the apparatus 500 or one component of the apparatus 500, the presence or absence of user contact with the apparatus 500, the orientation or acceleration/deceleration of the apparatus 500, and a change in temperature of the apparatus 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 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 514 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 516 is configured to facilitate communication between the apparatus 500 and other devices in a wired or wireless manner. The apparatus 500 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In one exemplary embodiment, the communication part 516 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 516 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 500 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, microcontrollers, microprocessors, or other electronic components for executing the methods described above.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 504, including instructions executable by processor 520 of apparatus 500 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
A non-transitory computer readable storage medium, which when executed by a processor of a mobile terminal, causes the mobile terminal to perform a method of determining a user tag, the method comprising:
performing natural language processing on input information of a target user;
acquiring fine-grained slot position information in the input information;
and deducing the fine granularity label of the target user based on the fine granularity slot position information.
In an optional implementation manner of the embodiment of the present application, the processing of the input information of the target user in natural language specifically includes:
Performing natural language processing on the input information by using a slot mining algorithm and an intention classifier; the slot digging algorithm comprises a slot digging template or a slot digging model.
In an alternative implementation manner of the embodiment of the present application, the method further includes:
Determining a target user cluster to which the target user belongs;
Based on the input information of the users in the target user cluster and the corresponding fine-grained slot position information, adjusting the slot position mining algorithm to obtain a new slot position mining algorithm;
The method comprises the following steps of performing natural language processing on input information by using a slot mining algorithm and an intention classifier, wherein the natural language processing is specifically as follows:
and carrying out natural language processing on the input information by utilizing the new slot mining algorithm and the intention classifier.
In an alternative implementation manner of the embodiment of the present application, the method further includes:
Deducing a person-set label of the target user based on the fine-grained slot position information;
Screening fine-granularity labels matched with the manual label from the fine-granularity labels;
and determining the target fine granularity label of the target user.
In an alternative implementation manner of the embodiment of the present application, the method further includes:
Determining a target user cluster to which the target user belongs;
If the target fine-grained labels of the preset number of users in the target user cluster comprise first target fine-grained labels, determining the first target fine-grained labels as target fine-grained labels of the users in the target user cluster;
The preset number is smaller than the number of users in the target user cluster.
In an optional implementation manner of the embodiment of the present application, the determining the target user cluster to which the target user belongs specifically includes:
Determining a target user cluster to which the target user belongs based on the related data of the target user and the related data of other users; the related data includes social data, attribute data, and/or behavioral data.
In an optional implementation manner of the embodiment of the present application, the determining, based on the related data of the target user and other users, a target user cluster to which the target user belongs includes:
Based on the related data of the target user and the related data of the other users, obtaining the similarity among the users;
constructing a user graph network based on the similarity among the users;
and determining a target user cluster to which the target user belongs based on the user graph network.
Fig. 6 is a schematic structural diagram of a server according to an embodiment of the present application. The server 600 may vary considerably in configuration or performance and may include one or more central processing units (central processing units, CPUs) 622 (e.g., one or more processors) and memory 632, one or more storage mediums 630 (e.g., one or more mass storage devices) that store applications 642 or data 644. Wherein memory 632 and storage medium 630 may be transitory or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 622 may be configured to communicate with a storage medium 630 and execute a series of instruction operations in the storage medium 630 on the server 600.
The server 600 may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input/output interfaces 658, one or more keyboards 656, and/or one or more operating systems 641 such as Windows ServerTM, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only of the preferred embodiment of the present application, and is not intended to limit the present application in any way. While the application has been described with reference to preferred embodiments, it is not intended to be limiting. Any person skilled in the art can make many possible variations and modifications to the technical solution of the present application or modifications to equivalent embodiments using the methods and technical contents disclosed above, without departing from the scope of the technical solution of the present application. Therefore, any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present application still fall within the scope of the technical solution of the present application.
Claims (8)
1. A method of determining a user tag, comprising:
Performing natural language processing on input information of a target user by using a slot mining algorithm and an intention classifier; the slot position excavation algorithm comprises a slot position excavation template or a slot position excavation model;
acquiring fine-grained slot position information in the input information;
deducing a fine granularity label of the target user based on the fine granularity slot position information;
Deducing a person-set label of the target user based on the fine-grained slot position information; the person of the target user sets a label for verifying the fine-grained label of the target user after deducing the fine-grained label of the target user;
Screening fine-granularity labels matched with the manual label from the fine-granularity labels;
determining a fine-grained label matched with the person-set label as a target fine-grained label of the target user; the target fine-grained label is different from the person-set label;
Determining a target user cluster to which the target user belongs;
If the target fine-grained labels of the preset number of users in the target user cluster comprise first target fine-grained labels, determining the first target fine-grained labels as target fine-grained labels of the users in the target user cluster; the preset number is smaller than the number of users in the target user cluster;
The method further comprises the steps of: based on the input information of other users in the target user cluster and the corresponding fine-grained slot position information, adjusting the slot position mining algorithm to obtain a new slot position mining algorithm; the natural language processing of the input information by using a slot mining algorithm and an intention classifier comprises the following steps: and carrying out natural language processing on the input information by utilizing the new slot mining algorithm and the intention classifier.
2. The method according to claim 1, wherein the determining the target user cluster to which the target user belongs is specifically:
Determining a target user cluster to which the target user belongs based on the related data of the target user and the related data of other users; the related data includes social data, attribute data, and/or behavioral data.
3. The method according to claim 2, wherein the determining the target user cluster to which the target user belongs based on the related data of the target user and other users includes:
Based on the related data of the target user and the related data of the other users, obtaining the similarity among the users;
constructing a user graph network based on the similarity among the users;
and determining a target user cluster to which the target user belongs based on the user graph network.
4. An apparatus for determining a user tag, comprising:
The processing unit is used for carrying out natural language processing on the input information of the target user by utilizing a slot mining algorithm and an intention classifier; the slot position excavation algorithm comprises a slot position excavation template or a slot position excavation model;
the obtaining unit is used for obtaining fine-grained slot position information in the input information;
a first deducing unit, configured to deduce a fine granularity tag of the target user based on the fine granularity slot information;
The second deducing unit is used for deducing the personal setting label of the target user based on the fine-granularity slot position information; the person of the target user sets a label for verifying the fine-grained label of the target user after deducing the fine-grained label of the target user;
The screening unit is used for screening the fine-granularity labels matched with the manual label from the fine-granularity labels;
The second determining unit is used for determining the fine-granularity label matched with the person-set label as a target fine-granularity label of the target user; the target fine-grained label is different from the person-set label;
a first determining unit, configured to determine a target user cluster to which the target user belongs;
A third determining unit, configured to determine, if target fine-grained labels of a preset number of users in the target user cluster include first target fine-grained labels, the first target fine-grained labels as target fine-grained labels of users in the target user cluster; the preset number is smaller than the number of users in the target user cluster;
the adjusting unit is used for adjusting the slot mining algorithm to obtain a new slot mining algorithm based on the input information of other users in the target user cluster and the corresponding fine-grained slot information;
The processing unit is specifically configured to perform natural language processing on the input information by using the new slot mining algorithm and the intention classifier.
5. The apparatus according to claim 4, wherein the first determining unit is specifically configured to:
Determining a target user cluster to which the target user belongs based on the related data of the target user and the related data of other users; the related data includes social data, attribute data, and/or behavioral data.
6. The apparatus according to claim 5, wherein the first determining unit includes:
An obtaining subunit, configured to obtain a similarity between each user based on the related data of the target user and the related data of the other users;
A construction subunit, configured to construct a user graph network based on the similarity between the users;
And the determining subunit is used for determining a target user cluster to which the target user belongs based on the user graph network.
7. An apparatus for determining a user tag, comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors to perform the method of determining a user tag of any of claims 1-3.
8. A machine readable medium having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the method of determining a user tag of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011521477.6A CN112632279B (en) | 2020-12-21 | 2020-12-21 | Method and related device for determining user tag |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011521477.6A CN112632279B (en) | 2020-12-21 | 2020-12-21 | Method and related device for determining user tag |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112632279A CN112632279A (en) | 2021-04-09 |
| CN112632279B true CN112632279B (en) | 2024-06-07 |
Family
ID=75320810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011521477.6A Active CN112632279B (en) | 2020-12-21 | 2020-12-21 | Method and related device for determining user tag |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112632279B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593690A (en) * | 2013-11-25 | 2014-02-19 | 北京光年无限科技有限公司 | User intelligent tagging system |
| EP2757493A2 (en) * | 2013-01-22 | 2014-07-23 | Maluuba Inc. | Natural language processing method and system |
| CN108268442A (en) * | 2017-12-19 | 2018-07-10 | 芋头科技（杭州）有限公司 | A kind of sentence Intention Anticipation method and system |
| CN111368219A (en) * | 2020-02-27 | 2020-07-03 | 广州腾讯科技有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN112016003A (en) * | 2020-08-19 | 2020-12-01 | 重庆邮电大学 | Social crowd user tag mining and similar user recommending method based on CNN |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106970993B (en) * | 2017-03-31 | 2020-09-18 | 百度在线网络技术（北京）有限公司 | Mining model updating method and device |
-
2020
- 2020-12-21 CN CN202011521477.6A patent/CN112632279B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2757493A2 (en) * | 2013-01-22 | 2014-07-23 | Maluuba Inc. | Natural language processing method and system |
| CN103593690A (en) * | 2013-11-25 | 2014-02-19 | 北京光年无限科技有限公司 | User intelligent tagging system |
| CN108268442A (en) * | 2017-12-19 | 2018-07-10 | 芋头科技（杭州）有限公司 | A kind of sentence Intention Anticipation method and system |
| CN111368219A (en) * | 2020-02-27 | 2020-07-03 | 广州腾讯科技有限公司 | Information recommendation method and device, computer equipment and storage medium |
| CN112016003A (en) * | 2020-08-19 | 2020-12-01 | 重庆邮电大学 | Social crowd user tag mining and similar user recommending method based on CNN |
Non-Patent Citations (2)
| Title |
|---|
| Web User Click Intention Prediction by Using Pupil Dilation Analysis;Joaquin Jadue et al;《Proceedings of the 2015 IEEE/WIC/ACM International Conference on Web Intelligent and Intelligent Agent Technology》;20151206(第01期);第433-436页 * |
| 基于用户查询意图识别的个性化搜索方法研究;林博;《中国优秀硕士学位论文全文数据库 信息科技辑》;20160515;第2016年卷(第05期);第I138-1505页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112632279A (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107919123B (en) | Multi-voice assistant control method, device and computer readable storage medium | |
| US10061762B2 (en) | Method and device for identifying information, and computer-readable storage medium | |
| EP3855360A1 (en) | Method and device for training image recognition model, and storage medium | |
| CN109359056B (en) | Application program testing method and device | |
| CN109961094B (en) | Sample acquisition method and device, electronic equipment and readable storage medium | |
| CN109961791B (en) | Voice information processing method and device and electronic equipment | |
| CN107666536B (en) | Method and device for searching terminal | |
| CN112101238A (en) | Clustering method and device, electronic equipment and storage medium | |
| CN111259967B (en) | Image classification and neural network training method, device, equipment and storage medium | |
| CN107659717B (en) | State detection method, device and storage medium | |
| US20160314164A1 (en) | Methods and devices for sharing cloud-based business card | |
| CN112651235A (en) | Poetry generation method and related device | |
| CN111753917A (en) | Data processing method, device and storage medium | |
| CN109981624B (en) | Intrusion detection method, device and storage medium | |
| CN112784151B (en) | Method and related device for determining recommended information | |
| CN110213062B (en) | Method and device for processing message | |
| CN112632279B (en) | Method and related device for determining user tag | |
| CN111860552A (en) | Model training method and device based on nuclear self-encoder and storage medium | |
| CN112784858B (en) | Image data processing method and device and electronic equipment | |
| CN113946228A (en) | Statement recommendation method and device, electronic equipment and readable storage medium | |
| CN113807540A (en) | Data processing method and device | |
| CN108345590B (en) | Translation method, translation device, electronic equipment and storage medium | |
| CN110020117B (en) | Interest information acquisition method and device and electronic equipment | |
| CN112767024B (en) | Advertisement creative generation method and related device | |
| CN110457560B (en) | Method for obtaining click rate and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |