CN113312905A - Information prediction method, information prediction device, storage medium and electronic equipment - Google Patents
Information prediction method, information prediction device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN113312905A CN113312905A CN202110698207.0A CN202110698207A CN113312905A CN 113312905 A CN113312905 A CN 113312905A CN 202110698207 A CN202110698207 A CN 202110698207A CN 113312905 A CN113312905 A CN 113312905A
- Authority
- CN
- China
- Prior art keywords
- word
- name
- person
- predicted
- vector
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 239000013598 vector Substances 0.000 claims abstract description 253
- 238000012549 training Methods 0.000 claims abstract description 94
- 239000011159 matrix material Substances 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 230000006403 short-term memory Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 230000015654 memory Effects 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 240000005373 Panax quinquefolius Species 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to an information prediction method, an information prediction device, a storage medium and an electronic device, which can obtain a word vector corresponding to each word in a name of a person to be predicted; determining a position vector corresponding to each word in the name of the person to be predicted, wherein the position vector is used for representing the position of the word in the name of the person to be predicted; and determining gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training according to the word vector and the position vector.
Description
Technical Field
The present disclosure relates to the field of gender identification based on names of people, and in particular, to an information prediction method, apparatus, storage medium, and electronic device.
Background
The technology of judging the gender of the user through the name of the user is widely applied to various scenes, such as the production of the voiced novel, a corresponding male speaker or a female speaker needs to be allocated to the role of the novel, and the users with different genders need to be distinguished and treated in the scenes of content push, network marketing, advertisement putting and the like in a network environment.
When gender judgment is carried out based on names in the related technology, a naive Bayes method can be adopted, and the probability that a certain character is male or female is obtained by calculating the probability that the certain character is male or female in a name database, wherein the method has certain deviation, for example, the 'Zhang winner' and 'Sheng' characters appear more in the name of the male, and the 'Man' characters also represent the male, but the 'Sheng' represents the female in many cases; or a machine learning-based binary classification model method in which a binary classification model is trained by extracting relevant features of words in names (e.g., the probability that a word is male or female), but the recognition accuracy is still low because the features and the model are simpler.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In a first aspect, an information prediction method is provided, and the method includes: acquiring a word vector corresponding to each word in the name of the person to be predicted; determining a position vector corresponding to each word in the name of the person to be predicted, wherein the position vector is used for representing the position of the word in the name of the person to be predicted; and determining gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training according to the word vector and the position vector.
In a second aspect, an information prediction apparatus is provided, the apparatus comprising: the first acquisition module is used for acquiring a word vector corresponding to each word in the name of the person to be predicted; the determining module is used for determining a position vector corresponding to each word in the name of the person to be predicted, and the position vector is used for representing the position of the word in the name of the person to be predicted; and the prediction module is used for determining the gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training according to the word vector and the position vector.
In a third aspect, a computer-readable medium is provided, on which a computer program is stored, which program, when being executed by a processing device, carries out the steps of the method according to the first aspect of the disclosure.
In a fourth aspect, an electronic device is provided, comprising: a storage device having a computer program stored thereon; processing means for executing the computer program in the storage means to implement the steps of the method of the first aspect of the present disclosure.
Through the technical scheme, a word vector corresponding to each word in the name of the person to be predicted is obtained; determining a position vector corresponding to each word in the name of the person to be predicted, wherein the position vector is used for representing the position of the word in the name of the person to be predicted; according to the word vectors and the position vectors, the gender information corresponding to the name of the person to be predicted is determined through a target gender prediction model obtained through pre-training, so that the gender corresponding to the name of the person to be predicted can be automatically recognized through the target gender prediction model, the influence of different positions of each word in the name of the person is enhanced through inputting the position information of each word in the name of the person into the target gender prediction model, and the accuracy of the model for recognizing the gender based on the name of the person can be improved.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale. In the drawings:
FIG. 1 is a flow chart illustrating a method of information prediction according to an exemplary embodiment;
FIG. 2 is a flow diagram illustrating a method of information prediction in accordance with an exemplary embodiment;
FIG. 3 is a flow diagram illustrating a method of information prediction in accordance with an exemplary embodiment;
FIG. 4 is a block diagram illustrating an information prediction apparatus according to an exemplary embodiment;
FIG. 5 is a block diagram illustrating an information prediction apparatus according to an exemplary embodiment;
fig. 6 is a block diagram illustrating a structure of an electronic device according to an example embodiment.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The gender identification method based on the name is mainly applied to a scene of gender judgment based on the name, and in a method (such as a naive Bayes method or a machine learning-based binary model method) for identifying the gender based on the name in the related technology, a certain deviation exists between an identification result and the actual gender, and the identification precision is low.
In order to solve the existing problems, the present disclosure provides an information prediction method, an information prediction apparatus, a storage medium, and an electronic device, which may input a word vector of each word in a name of a person to be predicted and a position vector of each word in the name of the person to be predicted together into a target gender prediction model, so as to predict gender information corresponding to the name of the person to be predicted through the target gender prediction model, and considering that different words in the name may affect the gender thereof at different positions, the influence of different positions of each word in the name of the person is strengthened by inputting the position information of each word in the name of the person into the target gender prediction model, thereby improving the accuracy of the model for identifying gender based on the name of the person.
Specific embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a flow chart illustrating a method of information prediction, as shown in fig. 1, according to an exemplary embodiment, the method comprising the steps of:
in step S101, a word vector corresponding to each word in the name of the person to be predicted is acquired.
For example, if the name to be predicted is a chinese name, the word vector is a word vector corresponding to each chinese character in the name to be predicted, and if the name to be predicted is the english name, the word vector is a word vector corresponding to each word in the name to be predicted, which is only an example herein, and this disclosure does not limit this, that is, the word herein includes but is not limited to a chinese character, a word, and the like.
In this step, the Word can be input into a Word2Vec model obtained by pre-training for each Word in the name of the person to be predicted, and the Word vector corresponding to the Word output by the Word2Vec model is obtained, wherein the Word vector output based on the Word2Vec model has good semantic characteristics, so that after the Word vector of each Word in the name of the person to be predicted is input into the model, the semantic characteristics of each Word can be obtained, and the gender information corresponding to the name of the person to be predicted can be more accurately identified according to the semantic characteristics of each Word in the full name.
It should be noted that, most of the existing methods for performing gender identification based on a first name only perform identification based on feature information of characters except for the last name, but in the present disclosure, a word vector of each character in the first name is input into a model for performing gender identification, including a word vector of a character corresponding to the last name, so that full name information can be learned through a deep learning model (i.e., a target gender prediction model in the present disclosure), and thus, the gender corresponding to the first name can be identified more accurately in consideration of the influence of the last name on the gender.
In addition, after the word vector corresponding to each word in the name of the person to be predicted is obtained, before the word vector is input into the target gender prediction model, in order to facilitate model calculation, normalization processing needs to be performed on the length of the word vector, taking the name of the Chinese character as an example, since the length of the name of the Chinese character generally does not exceed 4 words, the length of each name of the Chinese character can be uniformly set to 4, and the vector representation of the name of less than four words is subjected to filling processing, for example, the name of two words is "zhang san", the vector representation of the name of the person can be composed of "zhang" word vector + "three" word vector + zero vector, and for the name of three words, the vector representation of the name of the person can be composed of "zhang" word vector + "large" word vector + "three" word vector + zero vector.
In step S102, a position vector corresponding to each word in the name of the person to be predicted is determined, and the position vector is used for representing the position of the word in the name of the person to be predicted.
In this step, a preset dimension corresponding to the position vector may be obtained; aiming at each word in the name of the person to be predicted, acquiring the position information of the word in the name of the person to be predicted; and determining the position vector corresponding to the word according to the position information and the preset dimension.
The preset dimension is a vector dimension of the location vector, and the preset dimension may be set to 1 dimension according to actual needs, or may be set according to a common name length, for example, for a chinese name, the preset dimension may be set to a longest name length of 4, and the location information may be a number of bits of the word in the name to be predicted, for example, "zhang san," "zhang" is located at a first bit, and "zhang" is located at a second bit.
The following describes, by way of example, a process for determining a location vector corresponding to the word according to the location information and the preset dimension:
if the preset dimension is 1-dimensional, in a possible implementation, different preset identifiers may be used to represent different positions of the word in the name, for example, "zhang san", the position corresponding to the word "zhang" located at the first position may be represented by the preset identifier 1, and the position corresponding to the word "tri" located at the second position may be represented by the preset identifier 2, which has already been mentioned above, for the name whose name length is less than the preset length, zero padding processing is also performed, for example, for the name "zhang san", the position corresponding to the zero vector located at the third position and the fourth position is a zero vector, and for the zero vector in the name, the zero vector may be directly represented by the preset identifier 0, so that the position vector corresponding to the word "zhang" is [1], theposition vector corresponding to the word "tri" is [2], the position vector corresponding to the zero vector located at the third position and the fourth position is [0], "zhang san" may be represented by a combination of [1,2,0,0], the above examples are merely illustrative, and the present disclosure is not limited thereto.
Taking the name of chinese as an example, the preset dimension may be set to be the longest name length of 4, in which case, different positions of the word in the name may be represented by different position indexes, and further, for each word in the name, the vector element at the position index corresponding to the word may be set to be the first preset value,setting other vector elements in the position vector corresponding to the word to a second preset value different from the first preset value, for example, if the first preset value is 1, the second preset value may be set to 0, or when the first preset value is 0, the second preset value may be set to 1, so that the position vector corresponding to each word may be determined as follows: assuming that the preset dimension is 4, that is, the position vector corresponding to each word is 4 dimensions, taking "three" as an example, the position index corresponding to the "one" word located at the first position is "first position", the first vector element in the position vector corresponding to the "one" word may be set to 1, and the other vector elements may be set to 0, so as to obtain that the position vector corresponding to the "one" word is [1,0,0]Similarly, the position vector corresponding to the "three" word at the second bit is [0,1, 0]]Similarly, zero padding is also needed for "zhangsan", i.e. the position vector of the zero vector corresponding to the third bit of the name "zhangsan" may be [0,0,1,0]]The position vector of the zero vector corresponding to the fourth bit of the name "zhangsan" may be [0,0,0,1]That is, the combination of the position vectors for each word corresponding to "three" can be expressed as
The above examples are illustrative, and the disclosure is not limited thereto.
In step S103, according to the word vector and the position vector, gender information corresponding to the name of the person to be predicted is determined through a target gender prediction model obtained through pre-training.
In a possible implementation manner, the model structure of the target gender prediction model may include at least one LSTM (Long Short-Term Memory) network, at least one dense layer (i.e., a fully connected layer) connected to the LSTM network, and a softmax layer (i.e., a classification layer) connected to the dense layer.
In this step, for each word in the name of the person to be predicted, the word vector corresponding to the word and the position vector are spliced to obtain a first combined vector corresponding to the word; splicing the first combined vector corresponding to each word to obtain a first matrix; inputting the first matrix into the target gender prediction model to obtain a gender prediction result; and then determining the gender information corresponding to the name of the person to be predicted according to the gender prediction result.
The gender prediction result comprises a first probability that the name to be predicted belongs to a male and a second probability that the name to be predicted belongs to a female; in this way, the gender information corresponding to the target probability with the higher probability value in the first probability and the second probability can be used as the gender information corresponding to the name of the person to be predicted.
Illustratively, continuing to take the example of a chinese name whose preset length is set to 4, after obtaining a Word vector of each Word in the name to be predicted, zero padding processing needs to be performed on the name of less than 4 words, continuing to take the example of a name of "three", assuming that the Word vector corresponding to each Word is a 300-dimensional vector, then after outputting and performing zero padding processing based on the Word2Vec model, 4 300-dimensional Word vectors can be obtained, where the Word vector of the "one" Word can be represented as [ a1, a2,.. a.300 ], "three" Word can be represented as [ b1, b2,. a.b 300], and the zero vectors of the third and fourth bits after zero padding processing can be represented as [ c1, c2,. c300], [ d1, d2,. d.d 300], if it is determined that the position vector corresponding to the "one" Word "is [1]," position vector corresponding to the "three" Word, the position vector corresponding to the zero vector located at the third and fourth bits is [0], and for each word, the word vector and the position vector corresponding to the word are spliced to obtain the first combined vector corresponding to the word, for example, the word vector [ a1, a 2., a300] of the "sheet" word and the position vector [1] of the "sheet" word are spliced to obtain the first combined vector corresponding to the "sheet" word [ a1, a 2.,. a300,1], "word vector [ b1, b 2.,. b300] and" position vector [2] of the "three" word, and the first combined vector corresponding to the "three" word is [ b1, b2,. a.,. b300,2], the third and fourth bit vectors after zero processing are subjected to vector splicing in a similar way, the first combined vector can be [ c2, c2, c1, c300, and c 4934, respectively, d 2.., d300,0], such that stitching the first combined vector for each word yields a3 x 301 dimensional first matrix of the form:
or, if it is determined that the position vector corresponding to the word "one" is [1,0,0,0], "three" is [0,1,0,0], the position vector corresponding to the zero vector corresponding to the third bit of the name "three" is [0,0,1,0], the position vector corresponding to the zero vector corresponding to the fourth bit of the name "three" is [0,0,0,1], the word vector corresponding to the word and the position vector are spliced for each word to obtain the first combined vector corresponding to the word, for example, the word vector [ a1, a2,..,. a300] of the word "one" and the position vector [1,0,0,0] of the word "one" are spliced to obtain the first combined vector corresponding to the word "one" of the word [ a1, a2,. a300,1,0, 0], "three" is the word vector [ b. 1, b. 2,. 300] of the word "three" and the position vector of the word [0],300 ],0 ], 0,1,0] to obtain the first combined vector corresponding to the "three" word as [ b1, b 2.,. b300,0,0,1,0], and the first combined vector obtained after zero-padding the zero vectors of the third and fourth bits and performing vector splicing according to a similar method is [ c1, c 2.,. c300,0,0,1,0] and [ d1, d 2.,. d300,0,0,0,1], so that the first combined vector corresponding to each word can be spliced to obtain a3 x 304-dimensional first matrix in the following form:
in this way, the first matrix may be input into the target gender prediction model, a first probability that the name "zhang san" of the person to be predicted belongs to a male and a second probability that the name "zhang san" of the person to be predicted belongs to a female are obtained, and then gender information corresponding to a target probability with a higher probability value of the first probability and the second probability is used as the gender information corresponding to the name of the person to be predicted.
By adopting the method, the word vector of each word in the name of the person to be predicted and the position vector of each word in the name of the person to be predicted can be input into the target gender prediction model together, so that the gender information corresponding to the name of the person to be predicted can be automatically predicted through the target gender prediction model, and the influence of each word on different positions in the name is enhanced by inputting the position information of each word in the name of the person into the target gender prediction model, thereby improving the accuracy of the model for recognizing the gender based on the name of the person.
Fig. 2 is a flowchart illustrating an information prediction method according to an exemplary embodiment, in order to further improve the accuracy of the model for identifying gender based on the name, the present disclosure may further use the probability of each word in the name of the person to be predicted used in the name of the male person and the probability of each word in the name of the female person as the input of the model together with the word vector and the position vector, so that the model can more accurately identify the corresponding category of the name, as shown in fig. 2, before performing step S103, the method further includes the following steps:
in step S104, the statistical probability that each word in the name of the person to be predicted belongs to male and female respectively is obtained from a preset database.
The preset database may store a first statistical probability (the first statistical probability is used to represent the frequency of the word being used in the male name) and a second statistical probability (the second statistical probability is used to represent the frequency of the word being used in the female name) that each word in a preset corpus (the preset corpus stores all words used in the name and all surnames used in the name that can be counted) respectively belongs to the male name and the female name.
Thus, in the process of executing S103, the word vector, the position vector and the statistical probability corresponding to each word in the name of the person to be predicted may be input into the target gender prediction model together for gender recognition, fig. 3 is a flowchart illustrating an information prediction method according to an exemplary embodiment, and as shown in fig. 3, step S103 may be implemented by the following sub-steps:
in step S1031, for each word in the name of the person to be predicted, the word vector, the position vector, and the statistical probability corresponding to the word are spliced to obtain a second combined vector corresponding to the word.
The statistical probability corresponding to each word is a 2-dimensional vector, wherein one dimension is the statistical probability that the word corresponds to the name of a male person, and the other dimension is the statistical probability that the word corresponds to the name of a female person.
In step S1032, the second combination vectors corresponding to each word are spliced to obtain a second matrix.
In step S1033, the second matrix is input into the target gender prediction model, so as to determine gender information corresponding to the name of the person to be predicted by the target gender prediction model.
In the embodiment shown in fig. 3, the specific implementation process of splicing the word vector, the position vector, and the statistical probability corresponding to each word to obtain the second combined vector corresponding to the word, the specific implementation process of splicing the second combined vector corresponding to each word to obtain the second matrix, and the second matrix being input into the target gender prediction model, so that the specific implementation process of determining the gender corresponding to the name of the person to be predicted by using the target gender prediction model is similar to the implementation manner in step S103, and will not be described herein again.
A pre-training process of the target gender prediction model is described below, where the training process of the target gender prediction model is supervised model training, and specifically, for each of a plurality of training names, a training word vector corresponding to each word in the training name, a training position vector corresponding to each word in the training name, and a gender tag corresponding to the training name may be obtained, where the gender tag includes a gender corresponding to the training name; aiming at each character in the name of the training person, splicing the training character vector and the training position vector corresponding to the character to obtain a combined training vector corresponding to the character; splicing the combined training vectors corresponding to each character in the training name to obtain a training matrix; inputting the training matrix into a preset gender prediction model; and training the preset gender prediction model according to the output of the preset gender prediction model and the gender label so as to obtain the target gender prediction model.
In a possible training mode, a gender recognition result output by the model is subtracted from a gender label serving as a training label to obtain a loss function of the gender prediction model, then a back propagation algorithm is used to correct model parameters (for example, including weight and bias) of a preset gender prediction model to be trained with the goal of reducing the loss function, the above steps are repeated until the loss function meets a preset condition (for example, a function value of the loss function is smaller than a preset loss threshold) or the training is stopped when the training time reaches a preset time threshold, and then the model parameters when the training is stopped are used as target model parameters, so that the target gender prediction model is determined according to the target model parameters.
Fig. 4 is a block diagram illustrating an information prediction apparatus according to an exemplary embodiment, as shown in fig. 4, the apparatus including:
a first obtaining module 401, configured to obtain a word vector corresponding to each word in the name of the person to be predicted;
a determining module 402, configured to determine a position vector corresponding to each word in the name of the person to be predicted, where the position vector is used to represent a position of the word in the name of the person to be predicted;
and a predicting module 403, configured to determine, according to the word vector and the position vector, gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training.
Optionally, the first obtaining module 401 is configured to, for each Word in the name of the person to be predicted, input the Word into a Word2Vec model obtained through pre-training, so as to obtain the Word vector corresponding to the Word output by the Word2Vec model.
Optionally, the determining module 402 is configured to obtain a preset dimension corresponding to the position vector; aiming at each word in the name of the person to be predicted, acquiring the position information of the word in the name of the person to be predicted; and determining the position vector corresponding to the word according to the position information and the preset dimension.
Optionally, the predicting module 403 is configured to, for each word in the name of the person to be predicted, splice the word vector and the position vector corresponding to the word to obtain a first combined vector corresponding to the word; splicing the first combined vector corresponding to each word to obtain a first matrix; inputting the first matrix into the target gender prediction model to obtain a gender prediction result; and determining the gender information corresponding to the name of the person to be predicted according to the gender prediction result.
Optionally, the predicting module 403 is configured to determine, according to the word vector and the position vector, a first probability that the name to be predicted belongs to a male and a second probability that the name to be predicted belongs to a female through a target gender prediction model obtained through pre-training; and using the gender information corresponding to the target probability with the higher probability value in the first probability and the second probability as the gender information corresponding to the name of the person to be predicted.
Alternatively, fig. 5 is a block diagram of an information prediction apparatus according to the embodiment shown in fig. 4, and as shown in fig. 5, the apparatus further includes:
a second obtaining module 404, configured to obtain, from a preset database, statistical probabilities that each word in the name of the person to be predicted belongs to a male and a female, respectively;
the prediction module 403 is configured to, for each word in the name of the person to be predicted, splice the word vector, the position vector, and the statistical probability corresponding to the word to obtain a second combined vector corresponding to the word; splicing the second combination vector corresponding to each word to obtain a second matrix; and inputting the second matrix into the target gender prediction model so as to determine gender information corresponding to the name of the person to be predicted through the target gender prediction model.
Optionally, the target gender prediction model is obtained by training in the following manner:
aiming at each training person name in a plurality of training person names, acquiring a training word vector corresponding to each word in the training person name, a training position vector corresponding to each word in the training person name and a gender label corresponding to the training person name, wherein the gender label comprises gender corresponding to the training person name; aiming at each character in the name of the training person, splicing the training character vector and the training position vector corresponding to the character to obtain a combined training vector corresponding to the character; splicing the combined training vectors corresponding to each character in the training name to obtain a training matrix; inputting the training matrix into a preset gender prediction model; and training the preset gender prediction model according to the output of the preset gender prediction model and the gender label so as to obtain the target gender prediction model.
Optionally, the target gender prediction model comprises at least one layer of long-short term memory network LSTM, at least one fully connected dense layer connected with the LSTM and a softmax layer connected with the dense layer.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
By adopting the device, the word vector of each word in the name of the person to be predicted and the position vector of each word in the name of the person to be predicted can be input into the target gender prediction model together, so that the gender information corresponding to the name of the person to be predicted can be automatically predicted through the target gender prediction model, and the influence of each word on different positions in the name is strengthened by inputting the position information of each word in the name of the person into the target gender prediction model, so that the accuracy of the model for recognizing the gender based on the name of the person can be improved.
Referring now to FIG. 6, a schematic diagram of an electronic device (e.g., the gender identification terminal of FIG. 1) 600 suitable for implementing embodiments of the present disclosure is shown. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some implementations, the clients may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a word vector corresponding to each word in the name of the person to be predicted; determining a position vector corresponding to each word in the name of the person to be predicted, wherein the position vector is used for representing the position of the word in the name of the person to be predicted; and determining gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training according to the word vector and the position vector.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of a module does not in some cases constitute a limitation of the module itself, for example, the first retrieving module may also be described as a "module that retrieves a word vector".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Example 1 provides an information prediction method according to one or more embodiments of the present disclosure, including obtaining a word vector corresponding to each word in a name of a person to be predicted; determining a position vector corresponding to each word in the name of the person to be predicted, wherein the position vector is used for representing the position of the word in the name of the person to be predicted; and determining gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training according to the word vector and the position vector.
Example 2 provides the method of example 1, wherein the obtaining a word vector corresponding to each word in the name of the person to be predicted includes: and aiming at each Word in the name to be predicted, inputting the Word into a Word2Vec model obtained by pre-training to obtain the Word vector corresponding to the Word output by the Word2Vec model.
Example 3 provides the method of example 1, wherein determining a location vector corresponding to each word of the name of the person to be predicted comprises: acquiring a preset dimension corresponding to the position vector; for each word in the name of the person to be predicted, acquiring the position information of the word in the name of the person to be predicted; and determining the position vector corresponding to the word according to the position information and the preset dimension.
Example 4 provides the method of example 1, and the determining, according to the word vector and the position vector, gender information corresponding to the name of the person to be predicted by using a pre-trained target gender prediction model includes: for each word in the name to be predicted, splicing the word vector corresponding to the word and the position vector to obtain a first combined vector corresponding to the word; splicing the first combined vector corresponding to each word to obtain a first matrix; inputting the first matrix into the target gender prediction model to obtain a gender prediction result; and determining the gender information corresponding to the name of the person to be predicted according to the gender prediction result.
According to one or more embodiments of the present disclosure, example 5 provides the method of example 1, wherein determining, according to the word vector and the position vector, gender information corresponding to the name of the person to be predicted by using a pre-trained target gender prediction model includes: according to the word vector and the position vector, determining a first probability that the name of the person to be predicted belongs to a male and a second probability that the name of the person to be predicted belongs to a female through a target gender prediction model obtained through pre-training; and using the gender information corresponding to the target probability with the higher probability value in the first probability and the second probability as the gender information corresponding to the name of the person to be predicted.
Example 6 provides the method of example 1, before determining, according to the word vector and the position vector, gender information corresponding to the name of the person to be predicted by using a pre-trained target gender prediction model, the method further including:
acquiring the statistical probability that each word in the name of the person to be predicted belongs to male and female respectively from a preset database; the step of determining the gender information corresponding to the name of the person to be predicted according to the word vector and the position vector through a pre-trained target gender prediction model comprises the following steps: for each word in the name to be predicted, splicing the word vector, the position vector and the statistical probability corresponding to the word to obtain a second combined vector corresponding to the word; splicing the second combination vector corresponding to each word to obtain a second matrix; and inputting the second matrix into the target gender prediction model so as to determine gender information corresponding to the name of the person to be predicted through the target gender prediction model.
Example 7 provides the method of any one of examples 1-6, the target gender prediction model being trained in the following manner:
aiming at each training person name in a plurality of training person names, acquiring a training word vector corresponding to each word in the training person name, a training position vector corresponding to each word in the training person name and a gender label corresponding to the training person name, wherein the gender label comprises gender corresponding to the training person name; aiming at each character in the name of the training person, splicing the training character vector and the training position vector corresponding to the character to obtain a combined training vector corresponding to the character; splicing the combined training vectors corresponding to each word in the training name to obtain a training matrix; inputting the training matrix into a preset gender prediction model; and training the preset gender prediction model according to the output of the preset gender prediction model and the gender label so as to obtain the target gender prediction model.
Example 8 provides the method of example 7, the target gender prediction model including at least one layer of long-short term memory network, LSTM, at least one fully-connected dense layer connected to the LSTM, and a softmax layer connected to the dense layer.
Example 9 provides, in accordance with one or more embodiments of the present disclosure, an information prediction apparatus comprising: the first acquisition module is used for acquiring a word vector corresponding to each word in the name of the person to be predicted; the determining module is used for determining a position vector corresponding to each word in the name of the person to be predicted, and the position vector is used for representing the position of the word in the name of the person to be predicted; and the prediction module is used for determining the gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training according to the word vector and the position vector.
Example 10 provides a computer-readable medium having stored thereon a computer program that, when executed by a processing apparatus, performs the steps of the method of any one of examples 1-8, in accordance with one or more embodiments of the present disclosure.
Example 11 provides, in accordance with one or more embodiments of the present disclosure, an electronic device, comprising: a storage device having a computer program stored thereon; processing means for executing the computer program in the storage means to carry out the steps of the method of any one of examples 1-8.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims (11)
1. An information prediction method, the method comprising:
acquiring a word vector corresponding to each word in the name of the person to be predicted;
determining a position vector corresponding to each word in the name of the person to be predicted, wherein the position vector is used for representing the position of the word in the name of the person to be predicted;
and determining gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training according to the word vector and the position vector.
2. The method of claim 1, wherein the obtaining a word vector corresponding to each word in the name of the person to be predicted comprises:
and aiming at each Word in the name to be predicted, inputting the Word into a Word2Vec model obtained by pre-training to obtain the Word vector corresponding to the Word output by the Word2Vec model.
3. The method of claim 1, wherein the determining a position vector corresponding to each word of the name of the person to be predicted comprises:
acquiring a preset dimension corresponding to the position vector;
for each word in the name of the person to be predicted, acquiring the position information of the word in the name of the person to be predicted;
and determining the position vector corresponding to the word according to the position information and the preset dimension.
4. The method according to claim 1, wherein the determining, according to the word vector and the position vector, gender information corresponding to the name of the person to be predicted by using a pre-trained target gender prediction model comprises:
for each word in the name to be predicted, splicing the word vector corresponding to the word and the position vector to obtain a first combined vector corresponding to the word;
splicing the first combined vector corresponding to each word to obtain a first matrix;
inputting the first matrix into the target gender prediction model to obtain a gender prediction result;
and determining the gender information corresponding to the name of the person to be predicted according to the gender prediction result.
5. The method according to claim 1, wherein the determining, according to the word vector and the position vector, gender information corresponding to the name of the person to be predicted by using a pre-trained target gender prediction model comprises:
according to the word vector and the position vector, determining a first probability that the name of the person to be predicted belongs to a male and a second probability that the name of the person to be predicted belongs to a female through a target gender prediction model obtained through pre-training;
and using the gender information corresponding to the target probability with the higher probability value in the first probability and the second probability as the gender information corresponding to the name of the person to be predicted.
6. The method according to claim 1, wherein before the determining, according to the word vector and the position vector, gender information corresponding to the name of the person to be predicted by a pre-trained target gender prediction model, the method further comprises:
acquiring the statistical probability that each word in the name of the person to be predicted belongs to male and female respectively from a preset database;
the step of determining the gender information corresponding to the name of the person to be predicted according to the word vector and the position vector through a pre-trained target gender prediction model comprises the following steps:
for each word in the name to be predicted, splicing the word vector, the position vector and the statistical probability corresponding to the word to obtain a second combined vector corresponding to the word;
splicing the second combination vector corresponding to each word to obtain a second matrix;
and inputting the second matrix into the target gender prediction model so as to determine gender information corresponding to the name of the person to be predicted through the target gender prediction model.
7. The method of any one of claims 1-6, wherein the target gender prediction model is trained by:
aiming at each training person name in a plurality of training person names, acquiring a training word vector corresponding to each word in the training person name, a training position vector corresponding to each word in the training person name and a gender label corresponding to the training person name, wherein the gender label comprises gender corresponding to the training person name;
aiming at each character in the name of the training person, splicing the training character vector and the training position vector corresponding to the character to obtain a combined training vector corresponding to the character;
splicing the combined training vectors corresponding to each word in the training name to obtain a training matrix;
inputting the training matrix into a preset gender prediction model;
and training the preset gender prediction model according to the output of the preset gender prediction model and the gender label so as to obtain the target gender prediction model.
8. The method of claim 7 wherein said target gender prediction model comprises at least one layer of Long Short Term Memory (LSTM), at least one fully connected dense layer connected to said LSTM and a softmax layer connected to said dense layer.
9. An information prediction apparatus, characterized in that the apparatus comprises:
the first acquisition module is used for acquiring a word vector corresponding to each word in the name of the person to be predicted;
the determining module is used for determining a position vector corresponding to each word in the name of the person to be predicted, and the position vector is used for representing the position of the word in the name of the person to be predicted;
and the prediction module is used for determining the gender information corresponding to the name of the person to be predicted through a target gender prediction model obtained through pre-training according to the word vector and the position vector.
10. A computer-readable medium, on which a computer program is stored, characterized in that the program, when being executed by processing means, carries out the steps of the method of any one of claims 1 to 8.
11. An electronic device, comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110698207.0A CN113312905A (en) | 2021-06-23 | 2021-06-23 | Information prediction method, information prediction device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110698207.0A CN113312905A (en) | 2021-06-23 | 2021-06-23 | Information prediction method, information prediction device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113312905A true CN113312905A (en) | 2021-08-27 |
Family
ID=77380171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110698207.0A Withdrawn CN113312905A (en) | 2021-06-23 | 2021-06-23 | Information prediction method, information prediction device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113312905A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103389973A (en) * | 2013-07-23 | 2013-11-13 | 安阳师范学院 | Method for judging gender by utilizing Chinese name |
| CN104680130A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Chinese character recognition method for identification cards |
| CN111309913A (en) * | 2020-02-26 | 2020-06-19 | 北京慧博科技有限公司 | Method for analyzing gender by name |
| CN111339255A (en) * | 2020-02-26 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Target emotion analysis method, model training method, medium, and device |
| CN111652432A (en) * | 2020-06-01 | 2020-09-11 | 北京达佳互联信息技术有限公司 | Method and device for determining user attribute information, electronic equipment and storage medium |
| CN112016316A (en) * | 2020-08-31 | 2020-12-01 | 北京嘀嘀无限科技发展有限公司 | Identification method and system |
| CN112307744A (en) * | 2020-11-02 | 2021-02-02 | 安阳师范学院 | Method for judging gender of Chinese name based on multilayer perceptron |
-
2021
- 2021-06-23 CN CN202110698207.0A patent/CN113312905A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103389973A (en) * | 2013-07-23 | 2013-11-13 | 安阳师范学院 | Method for judging gender by utilizing Chinese name |
| CN104680130A (en) * | 2015-01-09 | 2015-06-03 | 安徽清新互联信息科技有限公司 | Chinese character recognition method for identification cards |
| CN111309913A (en) * | 2020-02-26 | 2020-06-19 | 北京慧博科技有限公司 | Method for analyzing gender by name |
| CN111339255A (en) * | 2020-02-26 | 2020-06-26 | 腾讯科技（深圳）有限公司 | Target emotion analysis method, model training method, medium, and device |
| CN111652432A (en) * | 2020-06-01 | 2020-09-11 | 北京达佳互联信息技术有限公司 | Method and device for determining user attribute information, electronic equipment and storage medium |
| CN112016316A (en) * | 2020-08-31 | 2020-12-01 | 北京嘀嘀无限科技发展有限公司 | Identification method and system |
| CN112307744A (en) * | 2020-11-02 | 2021-02-02 | 安阳师范学院 | Method for judging gender of Chinese name based on multilayer perceptron |
Non-Patent Citations (1)
| Title |
|---|
| 知乎: "用户画像之用户性别识别", Retrieved from the Internet <URL:《https://zhuanlan.zhihu.com/p/27480246》> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111767371A (en) | Intelligent question and answer method, device, equipment and medium | |
| WO2022166613A1 (en) | Method and apparatus for recognizing role in text, and readable medium and electronic device | |
| CN112766284B (en) | Image recognition method and device, storage medium and electronic equipment | |
| CN112883968B (en) | Image character recognition method, device, medium and electronic equipment | |
| CN113449070A (en) | Multimodal data retrieval method, device, medium and electronic equipment | |
| CN111368551A (en) | Method and device for determining event subject | |
| CN111460288B (en) | Method and device for detecting news event | |
| CN111883117A (en) | Voice wake-up method and device | |
| CN112364829A (en) | Face recognition method, device, equipment and storage medium | |
| CN111625649A (en) | Text processing method and device, electronic equipment and medium | |
| CN112149699A (en) | Method and device for generating model and method and device for recognizing image | |
| CN110634050B (en) | Method, device, electronic equipment and storage medium for identifying house source type | |
| CN111090993A (en) | Attribute alignment model training method and device | |
| CN114494709A (en) | Feature extraction model generation method, image feature extraction method and device | |
| CN114298007A (en) | Text similarity determination method, device, equipment and medium | |
| CN111915689B (en) | Method, apparatus, electronic device, and computer-readable medium for generating an objective function | |
| CN113033707A (en) | Video classification method and device, readable medium and electronic equipment | |
| CN112329454A (en) | Language identification method and device, electronic equipment and readable storage medium | |
| CN113111167A (en) | Method and device for extracting vehicle model of alarm receiving and processing text based on deep learning model | |
| CN116244431A (en) | Text classification method, device, medium and electronic equipment | |
| CN113033682B (en) | Video classification method, device, readable medium and electronic equipment | |
| CN113312905A (en) | Information prediction method, information prediction device, storage medium and electronic equipment | |
| CN114492400A (en) | Title entity recognition model training method, title entity recognition method and device | |
| CN110502630B (en) | Information processing method and device | |
| CN113420723A (en) | Method and device for acquiring video hotspot, readable medium and electronic 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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210827 |
|
| WW01 | Invention patent application withdrawn after publication |