CN111611388A - Account classification method, device and equipment - Google Patents
Account classification method, device and equipment Download PDFInfo
- Publication number
- CN111611388A CN111611388A CN202010475295.3A CN202010475295A CN111611388A CN 111611388 A CN111611388 A CN 111611388A CN 202010475295 A CN202010475295 A CN 202010475295A CN 111611388 A CN111611388 A CN 111611388A
- Authority
- CN
- China
- Prior art keywords
- samples
- classification
- content information
- ratio
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides an account classification method, an account classification device and account classification equipment, wherein the account classification method comprises the following steps: acquiring the total number of posts of a target account and the content information of each post; respectively inputting the content information of each post into a preset classification model to obtain at least one classification label of each post; calculating a ratio of the number of posts corresponding to each of the category labels to the total number of posts; and determining the type of the target account according to the ratio. The method and the device for classifying the account number improve efficiency and accuracy of classifying the account number.
Description
Technical Field
The application relates to the technical field of computers, in particular to an account classification method, device and equipment.
Background
With the coming of the internet era, social networks increasingly become important components in people's lives, people can use social accounts to post opinions on the social networks to share their thoughts, and in the process, users with high popularity and strong call will appear, the users are called KOL (Key Opinion Leader), most of the social accounts of KOL have more fans, so that the information posted by KOL on the social accounts is high in attention and has certain influence.
When selecting the KOL, the KOL often needs to be classified, in the prior art, classification is generally performed according to profile description or authentication information filled by a user, accuracy is low, and when the user does not fill information related to account categories, classification of social accounts cannot be performed.
Disclosure of Invention
The embodiment of the application aims to provide an account classifying method, device and equipment, which are used for improving the efficiency and accuracy of classifying accounts.
A first aspect of the embodiments of the present application provides an account classification method, including: acquiring the total number of posts of a target account and the content information of each post; respectively inputting the content information of each post into a preset classification model to obtain at least one classification label of each post; calculating a ratio of the number of posts corresponding to each of the category labels to the total number of posts; and determining the type of the target account according to the ratio.
In an embodiment, the step of constructing the predetermined classification model includes: acquiring content information of a plurality of samples and classification labels of the plurality of samples; performing feature extraction on the content information of the plurality of samples to obtain feature data of the plurality of samples; and constructing the preset classification model according to the classification labels of the samples and the characteristic data.
In an embodiment, the performing feature extraction on the content information of the multiple samples to obtain feature data of the multiple samples includes: preprocessing the content information of the plurality of samples to obtain preprocessed data; vectorizing the preprocessed data to obtain word vector data of the multiple samples; and performing convolution pooling on the word vector data to obtain the feature data of the plurality of samples.
In an embodiment, the preprocessing the content information of the plurality of samples to obtain preprocessed data includes: performing word segmentation processing on the content information of the plurality of samples; and removing stop words in the content information of the plurality of samples after word segmentation processing.
In an embodiment, the determining the type of the target account according to the ratio includes: judging whether the ratio is larger than a preset threshold value or not; when the ratio is greater than the preset threshold, determining the classification label corresponding to the ratio as the type of the target account.
A second aspect of the embodiments of the present application provides an account classifying device, including: the acquisition module is used for acquiring the posting total number of the target account and the content information of each post; the classification module is used for respectively inputting the content information of each post into a preset classification model to obtain at least one classification label of each post; a calculation module for calculating a ratio of the number of posts corresponding to each of the classification tags to the total number of posts; and the determining module is used for determining the type of the target account according to the ratio.
In an embodiment, the system further includes a building module configured to: acquiring content information of a plurality of samples and classification labels of the plurality of samples; performing feature extraction on the content information of the plurality of samples to obtain feature data of the plurality of samples; and constructing the preset classification model according to the classification labels of the samples and the characteristic data.
In an embodiment, the building module is specifically configured to: preprocessing the content information of the plurality of samples to obtain preprocessed data; vectorizing the preprocessed data to obtain word vector data of the multiple samples; and performing convolution pooling on the word vector data to obtain the feature data of the plurality of samples.
In an embodiment, the building module is specifically configured to: performing word segmentation processing on the content information of the plurality of samples; and removing stop words in the content information of the plurality of samples after word segmentation processing.
In one embodiment, the determining module is configured to: judging whether the ratio is larger than a preset threshold value or not; when the ratio is greater than the preset threshold, determining the classification label corresponding to the ratio as the type of the target account.
A third aspect of embodiments of the present application provides an electronic device, including: a memory to store a computer program; a processor configured to perform the method of the first aspect of the embodiments of the present application and any of the embodiments of the present application.
A fourth aspect of embodiments of the present application provides a non-transitory electronic device-readable storage medium, including: a program which, when run by an electronic device, causes the electronic device to perform the method of the first aspect of an embodiment of the present application and any embodiment thereof.
In the embodiment of the application, the historical posting contents of the account numbers to be classified are obtained, the historical posting contents of the account numbers to be classified are classified through the preset classification model, the types of the account numbers to be classified are finally determined according to the proportion of the posting amount of each type in the total posting amount, and the efficiency and the accuracy of classifying the account numbers are effectively improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 2 is a schematic flowchart of an account classification method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating a process of constructing a predetermined classification model according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an account classifying device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an account classifying device according to another embodiment of the present application.
Reference numerals:
100-electronic equipment, 110-bus, 120-processor, 130-memory, 400-account classification device, 410-acquisition module, 420-classification module, 430-calculation module, 440-determination module, 450-construction module.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
In the description of the present application, the terms "first," "second," and the like are used for distinguishing between descriptions and do not denote an order of magnitude, nor are they to be construed as indicating or implying relative importance.
In the description of the present application, the terms "mounted," "disposed," "provided," "connected," and "configured" are to be construed broadly unless expressly stated or limited otherwise. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be mechanically or electrically connected; either directly or indirectly through intervening media, or may be internal to two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
Please refer to fig. 1, which is a schematic structural diagram of an electronic device 100 according to an embodiment of the present application, and includes at least one processor 120 and a memory 130, where fig. 1 illustrates one processor as an example. The processors 120 and the memory 130 are coupled by a bus 110, and the memory 130 stores instructions executable by the at least one processor 120, the instructions being executable by the at least one processor 120 to cause the at least one processor 120 to perform an account classification method as in the embodiments described below.
As shown in fig. 2, which is a flowchart illustrating an account classification method according to an embodiment of the present disclosure, the method may be executed by the electronic device 100 shown in fig. 1 to improve efficiency and accuracy of classifying accounts. The method comprises the following steps:
step 210: and acquiring the posting total number of the target account and the content information of each post.
In the above steps, the target account may be an account registered on various social platforms, including but not limited to: microblog account numbers, public numbers, bar account numbers, and the like. An API (Application Programming Interface), a web crawler, or the like may be used to obtain the total number of posts of the target account and content information of each post, where the content information may include text information, pictures, audio, video, and the like.
Step 220: and respectively inputting the content information of each post into a preset classification model to obtain at least one classification label of each post.
In the above steps, a preset classification model may be pre-constructed in a machine learning manner, then the content information of each post is respectively input into the preset classification model, and the preset classification model outputs a corresponding classification tag according to the characteristics of the content information of each post, where each post may have one or more classification tags, and the classification tags include but are not limited to: travel, food, photography, music, sports, etc.
Step 230: a ratio of the number of posts corresponding to each category label to the total number of posts is calculated.
In the above step, assuming that the total number of posts of the target account is X, the number of posts corresponding to the first classification label is X1The number of posts corresponding to the second category label is x2The number of posts corresponding to the third category label is x3The number of posts corresponding to the fourth category label is x4Then the ratio of the number of posts corresponding to each classification label to the total number of posts is calculated, the ratio of the first classification label is (x)1/X), the ratio of the second classification label is (X)2/X), the ratio of the third classification label is (X)3/X), the ratio of the fourth class label is (X)4/X), and so on.
Step 240: and determining the type of the target account according to the ratio.
In the above step, it may be determined whether the ratio of the classification labels is greater than a preset threshold, and when the ratio is greater than the preset threshold, the classification label corresponding to the ratio is determined as the type of the target account. The type of the target account may be one or more, and all classification tags with a ratio greater than a preset threshold may be determined as the type of the target account. The preset threshold may be set in a range from 0 to 1 according to an actual situation, in an embodiment, the preset threshold is 0.5, and the classification label with the ratio greater than 0.5 is determined as the type of the target account.
In an embodiment, different preset thresholds may be set for each classification label according to browsing amount, reading amount, forwarding amount, or the like of different classification labels, whether the ratio of the classification label is greater than the preset threshold corresponding to the classification label is determined, and when the ratio of the classification label is greater than the preset threshold corresponding to the classification label, the classification label is determined as the type of the target account.
In an embodiment, the ratio of the classification labels may be sorted according to size, and the classification label with the largest ratio is determined as the type of the target account.
As shown in fig. 3, which is a schematic flowchart illustrating a process of constructing a preset classification model according to an embodiment of the present application, the method may be executed by the electronic device 100 shown in fig. 1, and the method includes the following steps:
step 310: content information of the plurality of samples and classification labels of the plurality of samples are obtained.
In the above steps, the classification labels of the samples are obtained by means of manual labeling, the content information of each sample is manually checked, and the classification label of each sample is judged and labeled.
Step 320: and performing feature extraction on the content information of the plurality of samples to obtain feature data of the plurality of samples.
In the above steps, the content information of the multiple samples is preprocessed to obtain preprocessed data, the preprocessed data is vectorized to obtain word vector data of the multiple samples, and the word vector data is convolved in a pooling manner to obtain feature data of the multiple samples.
In one embodiment, the preprocessing the content information of the plurality of samples includes: and performing word segmentation processing on the content information of the plurality of samples, and removing stop words in the content information of the plurality of samples after word segmentation processing. The word segmentation processing is to divide the text of the content information to form a series of word sequences, and the removal of stop words is to remove some words without practical meaning, such as punctuation, numbers, symbols, "and", "and the like.
Step 330: and constructing a preset classification model according to the classification labels and the characteristic data of the samples.
In an embodiment, a convolutional neural network may be used to perform convolutional pooling on the word vector data to obtain feature data of a plurality of samples. The input of the convolutional neural network is a word vector matrix, a plurality of convolutional cores with different sizes are used for carrying out convolutional calculation on the convolutional layer to obtain a plurality of characteristic matrices, then the largest pooling is used for sampling the plurality of characteristic matrices in the pooling layer, the characteristic matrix with the largest value is reserved, other characteristic matrices with smaller values are abandoned, and characteristic data are obtained. And finally, inputting the characteristic data into a full connection layer for classification, comparing the classification result with the classification labels of the multiple samples, and carrying out optimization adjustment until the classification result is consistent with the classification labels of the multiple samples, thereby obtaining a trained preset classification model.
In an embodiment, the preset classification model may be constructed based on a fasttext model, word vector data is directly added to obtain an average value, a text vector is obtained, a classification result is obtained through an output layer, the classification result is compared with the classification labels of the multiple samples, optimization adjustment is performed until the classification result is consistent with the classification labels of the multiple samples, and the trained preset classification model is obtained.
As shown in fig. 4, which is a schematic structural diagram of an account classifying device 400 according to an embodiment of the present application, the device can be applied to the electronic device 100 shown in fig. 1, and includes: an acquisition module 410, a classification module 420, a calculation module 430, and a determination module 440. The principle relationship of the modules is as follows:
and the obtaining module 410 is used for obtaining the posting total number of the target account and the content information of each post. For details, see the description of step 210 in the above embodiment.
The classification module 420 is configured to input the content information of each post into a preset classification model, so as to obtain at least one classification tag of each post. See the description of step 220 in the above embodiment for details.
A calculation module 430 for calculating a ratio of the number of posts corresponding to each category label to the total number of posts. See the description of step 230 in the above embodiment for details.
And a determining module 440, configured to determine the type of the target account according to the ratio. See the description of step 240 in the above embodiment for details.
In one embodiment, the determining module 440 is configured to: judging whether the ratio is greater than a preset threshold value or not; and when the ratio is larger than a preset threshold value, determining the classification label corresponding to the ratio as the type of the target account. See the description of step 240 in the above embodiment for details.
As shown in fig. 5, which is a schematic structural diagram of an account classifying device 400 according to an embodiment of the present application, the device can be applied to the electronic device 100 shown in fig. 1, and includes: an acquisition module 410, a classification module 420, a calculation module 430, a determination module 440, and a construction module 450.
In one embodiment, the building block 450 is configured to: acquiring content information of a plurality of samples and classification labels of the plurality of samples; performing feature extraction on the content information of the plurality of samples to obtain feature data of the plurality of samples; and constructing a preset classification model according to the classification labels and the characteristic data of the samples. For details, refer to the descriptions of step 310 to step 330 in the above embodiments.
In one embodiment, the building module 450 is specifically configured to: preprocessing the content information of the plurality of samples to obtain preprocessed data; vectorizing the preprocessed data to obtain word vector data of a plurality of samples; and performing convolution pooling on the word vector data to obtain feature data of a plurality of samples. See the description of step 320 in the above embodiment for details.
In one embodiment, the building module 450 is specifically configured to: performing word segmentation processing on the content information of the plurality of samples; and removing stop words in the content information of the plurality of samples after word segmentation processing. See the description of step 320 in the above embodiment for details.
For a detailed description of the account classifying device 400, please refer to the description of the related method steps in the above embodiments.
An embodiment of the present invention further provides a storage medium readable by an electronic device, including: a program that, when run on an electronic device, causes the electronic device to perform all or part of the procedures of the methods in the above-described embodiments. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid-State Drive (SSD), or the like. The storage medium may also comprise a combination of memories of the kind described above.
The above are merely preferred embodiments of the present application and are not intended to limit the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. An account number classification method is characterized by comprising the following steps:
acquiring the total number of posts of a target account and the content information of each post;
respectively inputting the content information of each post into a preset classification model to obtain at least one classification label of each post;
calculating a ratio of the number of posts corresponding to each of the category labels to the total number of posts;
and determining the type of the target account according to the ratio.
2. The method of claim 1, wherein the step of constructing the pre-set classification model comprises:
acquiring content information of a plurality of samples and classification labels of the plurality of samples;
performing feature extraction on the content information of the plurality of samples to obtain feature data of the plurality of samples;
and constructing the preset classification model according to the classification labels of the samples and the characteristic data.
3. The method according to claim 2, wherein the performing feature extraction on the content information of the plurality of samples to obtain feature data of the plurality of samples comprises:
preprocessing the content information of the plurality of samples to obtain preprocessed data;
vectorizing the preprocessed data to obtain word vector data of the multiple samples;
and performing convolution pooling on the word vector data to obtain the feature data of the plurality of samples.
4. The method of claim 3, wherein the preprocessing the content information of the plurality of samples to obtain preprocessed data comprises:
performing word segmentation processing on the content information of the plurality of samples;
and removing stop words in the content information of the plurality of samples after word segmentation processing.
5. The method of claim 1, wherein determining the type of the target account number according to the ratio comprises:
judging whether the ratio is larger than a preset threshold value or not;
when the ratio is greater than the preset threshold, determining the classification label corresponding to the ratio as the type of the target account.
6. An account number classification device, comprising:
the acquisition module is used for acquiring the posting total number of the target account and the content information of each post;
the classification module is used for respectively inputting the content information of each post into a preset classification model to obtain at least one classification label of each post;
a calculation module for calculating a ratio of the number of posts corresponding to each of the classification tags to the total number of posts;
and the determining module is used for determining the type of the target account according to the ratio.
7. The apparatus of claim 6, further comprising a construction module to:
acquiring content information of a plurality of samples and classification labels of the plurality of samples;
performing feature extraction on the content information of the plurality of samples to obtain feature data of the plurality of samples;
and constructing the preset classification model according to the classification labels of the samples and the characteristic data.
8. The apparatus of claim 7, wherein the build module is configured to:
preprocessing the content information of the plurality of samples to obtain preprocessed data;
vectorizing the preprocessed data to obtain word vector data of the multiple samples;
and performing convolution pooling on the word vector data to obtain the feature data of the plurality of samples.
9. The apparatus of claim 6, wherein the determining module is configured to:
judging whether the ratio is larger than a preset threshold value or not;
when the ratio is greater than the preset threshold, determining the classification label corresponding to the ratio as the type of the target account.
10. An electronic device, comprising:
a memory to store a computer program;
a processor to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010475295.3A CN111611388A (en) | 2020-05-29 | 2020-05-29 | Account classification method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010475295.3A CN111611388A (en) | 2020-05-29 | 2020-05-29 | Account classification method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111611388A true CN111611388A (en) | 2020-09-01 |
Family
ID=72203867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010475295.3A Pending CN111611388A (en) | 2020-05-29 | 2020-05-29 | Account classification method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111611388A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112464106A (en) * | 2020-11-26 | 2021-03-09 | 上海哔哩哔哩科技有限公司 | Object recommendation method and device |
| CN113033675A (en) * | 2021-03-30 | 2021-06-25 | 长沙理工大学 | Image classification method and device and computer equipment |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104901847A (en) * | 2015-05-27 | 2015-09-09 | 国家计算机网络与信息安全管理中心 | Social network zombie account detection method and device |
| CN105787025A (en) * | 2016-02-24 | 2016-07-20 | 腾讯科技（深圳）有限公司 | Network platform public account classifying method and device |
| CN106886518A (en) * | 2015-12-15 | 2017-06-23 | 国家计算机网络与信息安全管理中心 | A kind of method of microblog account classification |
| CN107025284A (en) * | 2017-04-06 | 2017-08-08 | 中南大学 | The recognition methods of network comment text emotion tendency and convolutional neural networks model |
| CN109145937A (en) * | 2018-06-25 | 2019-01-04 | 北京达佳互联信息技术有限公司 | A kind of method and device of model training |
| CN109492091A (en) * | 2018-09-28 | 2019-03-19 | 科大国创软件股份有限公司 | A kind of complaint work order intelligent method for classifying based on convolutional neural networks |
| CN109492109A (en) * | 2018-11-22 | 2019-03-19 | 北京神州泰岳软件股份有限公司 | A kind of information hot spot method for digging and device |
| CN109739986A (en) * | 2018-12-28 | 2019-05-10 | 合肥工业大学 | A kind of complaint short text classification method based on Deep integrating study |
| CN110598011A (en) * | 2019-09-27 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Data processing method, data processing device, computer equipment and readable storage medium |
| CN110633373A (en) * | 2018-06-20 | 2019-12-31 | 上海财经大学 | Automobile public opinion analysis method based on knowledge graph and deep learning |
| CN110705592A (en) * | 2019-09-03 | 2020-01-17 | 平安科技（深圳）有限公司 | Classification model training method, device, equipment and computer readable storage medium |
| CN110990571A (en) * | 2019-12-02 | 2020-04-10 | 精硕科技（北京）股份有限公司 | Method and device for obtaining discussion occupation ratio, storage medium and electronic equipment |
-
2020
- 2020-05-29 CN CN202010475295.3A patent/CN111611388A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104901847A (en) * | 2015-05-27 | 2015-09-09 | 国家计算机网络与信息安全管理中心 | Social network zombie account detection method and device |
| CN106886518A (en) * | 2015-12-15 | 2017-06-23 | 国家计算机网络与信息安全管理中心 | A kind of method of microblog account classification |
| CN105787025A (en) * | 2016-02-24 | 2016-07-20 | 腾讯科技（深圳）有限公司 | Network platform public account classifying method and device |
| CN107025284A (en) * | 2017-04-06 | 2017-08-08 | 中南大学 | The recognition methods of network comment text emotion tendency and convolutional neural networks model |
| CN110633373A (en) * | 2018-06-20 | 2019-12-31 | 上海财经大学 | Automobile public opinion analysis method based on knowledge graph and deep learning |
| CN109145937A (en) * | 2018-06-25 | 2019-01-04 | 北京达佳互联信息技术有限公司 | A kind of method and device of model training |
| CN109492091A (en) * | 2018-09-28 | 2019-03-19 | 科大国创软件股份有限公司 | A kind of complaint work order intelligent method for classifying based on convolutional neural networks |
| CN109492109A (en) * | 2018-11-22 | 2019-03-19 | 北京神州泰岳软件股份有限公司 | A kind of information hot spot method for digging and device |
| CN109739986A (en) * | 2018-12-28 | 2019-05-10 | 合肥工业大学 | A kind of complaint short text classification method based on Deep integrating study |
| CN110705592A (en) * | 2019-09-03 | 2020-01-17 | 平安科技（深圳）有限公司 | Classification model training method, device, equipment and computer readable storage medium |
| CN110598011A (en) * | 2019-09-27 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Data processing method, data processing device, computer equipment and readable storage medium |
| CN110990571A (en) * | 2019-12-02 | 2020-04-10 | 精硕科技（北京）股份有限公司 | Method and device for obtaining discussion occupation ratio, storage medium and electronic equipment |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112464106A (en) * | 2020-11-26 | 2021-03-09 | 上海哔哩哔哩科技有限公司 | Object recommendation method and device |
| CN112464106B (en) * | 2020-11-26 | 2022-12-13 | 上海哔哩哔哩科技有限公司 | Object recommendation method and device |
| CN113033675A (en) * | 2021-03-30 | 2021-06-25 | 长沙理工大学 | Image classification method and device and computer equipment |
| CN113033675B (en) * | 2021-03-30 | 2022-07-01 | 长沙理工大学 | Image classification method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108874776B (en) | Junk text recognition method and device | |
| CN107707545B (en) | Abnormal webpage access fragment detection method, device, equipment and storage medium | |
| CN109189767B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN112861648B (en) | Character recognition method, character recognition device, electronic equipment and storage medium | |
| CN109492222A (en) | Intension recognizing method, device and computer equipment based on conceptional tree | |
| CN107346433A (en) | A kind of text data sorting technique and server | |
| CN112560453B (en) | Voice information verification method and device, electronic equipment and medium | |
| CN110083832B (en) | Article reprint relation identification method, device, equipment and readable storage medium | |
| CN113626607B (en) | Abnormal work order identification method and device, electronic equipment and readable storage medium | |
| CN110555713A (en) | method and device for determining sales prediction model | |
| CN111611388A (en) | Account classification method, device and equipment | |
| US20160283582A1 (en) | Device and method for detecting similar text, and application | |
| WO2019056496A1 (en) | Method for generating picture review probability interval and method for picture review determination | |
| CN116029280A (en) | Method, device, computing equipment and storage medium for extracting key information of document | |
| CN114037518A (en) | Risk prediction model construction method and device, electronic equipment and storage medium | |
| CN111444364B (en) | Image detection method and device | |
| CN113705201B (en) | Text-based event probability prediction evaluation algorithm, electronic device and storage medium | |
| WO2019136920A1 (en) | Presentation method for visualization of topic evolution, application server, and computer readable storage medium | |
| CN112507912B (en) | Method and device for identifying illegal pictures | |
| CN114706948A (en) | News processing method and device, storage medium and electronic equipment | |
| CN114579876A (en) | False information detection method, device, equipment and medium | |
| CN113468396A (en) | Webpage classification method, device and equipment based on meta tags | |
| CN115883111A (en) | Phishing website identification method and device, electronic equipment and storage medium | |
| CN113221035A (en) | Method, apparatus, device, medium, and program product for determining an abnormal web page | |
| CN108304540B (en) | Text data identification method and device and related equipment |
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 |