CN117194792B - Child drawing recommendation method and system based on role prediction - Google Patents
Child drawing recommendation method and system based on role prediction Download PDFInfo
- Publication number
- CN117194792B CN117194792B CN202311207389.2A CN202311207389A CN117194792B CN 117194792 B CN117194792 B CN 117194792B CN 202311207389 A CN202311207389 A CN 202311207389A CN 117194792 B CN117194792 B CN 117194792B
- Authority
- CN
- China
- Prior art keywords
- user
- reading
- role
- parameters
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 83
- 238000013515 script Methods 0.000 claims abstract description 34
- 238000012216 screening Methods 0.000 claims abstract description 11
- 238000005070 sampling Methods 0.000 claims description 64
- 238000012549 training Methods 0.000 claims description 41
- 238000000638 solvent extraction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000010422 painting Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a child drawing recommendation method and system based on role prediction, wherein the method comprises the following steps: acquiring user parameters of a target user, and starting equipment operation and drawing software operation in a historical time period; the user parameters comprise user identity parameters and user history parameters; predicting a reading role corresponding to the target user based on a reading role prediction algorithm model according to the user parameters of the target user; predicting the user maturity corresponding to the target user based on an operation maturity prediction algorithm model according to the starting equipment operation and the script software operation; and screening out a target script from a candidate script database according to the reading role and the user maturity so as to recommend the target script to the target user. Therefore, the method and the device can comprehensively utilize the algorithm model and the user parameters to improve the rationality and the accuracy of the drawing recommendation and improve the user experience.
Description
Technical Field
The invention relates to the technical field of data recommendation, in particular to a child drawing recommendation method and system based on role prediction.
Background
With the improvement of the importance degree of early painting reading education for children, more and more reading software begins to attach importance to the research and development of the painting recommendation algorithm technology so as to improve the recommendation accuracy of the children painting for users.
However, in the prior art, when the recommendation of children's drawing is realized, the drawing in the database is generally screened and matched only through the conventional user requirement, and more user parameters and user operations are not considered to determine the roles and maturity of the users, so that the recommendation effect is poor. It can be seen that the prior art has defects and needs to be solved.
Disclosure of Invention
The invention aims to solve the technical problem of providing a child drawing recommendation method and system based on role prediction, which can comprehensively utilize an algorithm model and user parameters to improve the rationality and accuracy of drawing recommendation and improve user experience.
In order to solve the technical problems, the first aspect of the invention discloses a children's painting recommendation method based on role prediction, which comprises the following steps:
acquiring user parameters of a target user, and starting equipment operation and drawing software operation in a historical time period; the user parameters comprise user identity parameters and user history parameters;
Predicting a reading role corresponding to the target user based on a reading role prediction algorithm model according to the user parameters of the target user;
predicting the user maturity corresponding to the target user based on an operation maturity prediction algorithm model according to the starting equipment operation and the script software operation;
and screening out a target script from a candidate script database according to the reading role and the user maturity so as to recommend the target script to the target user.
As an optional implementation manner, in the first aspect of the present invention, the user identity parameters include a user age, a user gender, a user level, and a user physical parameter; the user history parameters include a user history sound record, a user history reading book record, a user history browsing data record, a user history focusing book record and a user history commentary book record.
As an optional implementation manner, in the first aspect of the present invention, the operation of the boot device includes at least one of a boot gesture operation, a boot key operation, a boot input password operation, and a boot browsing page operation that are made by the target user for a reading device; and/or the drawing software operation comprises at least one of an in-software browsing operation, an in-software page switching operation, an in-software selecting operation and an in-software information input operation which are made by the target user aiming at the drawing reading software.
In an optional implementation manner, in a first aspect of the present invention, the predicting, based on a reading role prediction algorithm model, the reading role corresponding to the target user according to the user parameter of the target user includes:
inputting all data in the user history parameters of the target user into a trained reading role prediction algorithm model to obtain predicted reading roles corresponding to all data in the user history parameters; the reading role prediction algorithm model is obtained through training a training data set comprising a plurality of training user history parameters and corresponding reading role labels;
determining character identity parameters corresponding to the predicted reading characters according to the predicted reading characters and the corresponding relation between the preset characters and the identities;
calculating first parameter similarity between the character identity parameters and the user identity parameters, judging whether the first parameter similarity is larger than a first similarity threshold, and if so, determining the predicted reading character as the reading character corresponding to the target user;
if not, based on a random sampling algorithm and the reading role prediction algorithm model, re-predicting the reading role corresponding to the target user according to the user history parameters; the predicted reading role, the reading role or the reading role label comprises at least one of an adult reading role before sleeping, a child reading role before sleeping, an adult accompanying reading role, a child reading role in morning, a child reading role and a child image-text reading role.
In an optional implementation manner, in a first aspect of the present invention, the predicting, based on the random sampling algorithm and the reading role prediction algorithm model, the reading role corresponding to the target user according to the user history parameter includes:
randomly sampling data in user history parameters of the target user to obtain a plurality of sampled data, and inputting each sampled data to the reading role prediction algorithm model to obtain a sampling prediction reading role and a prediction probability corresponding to each sampled data;
calculating the similarity of the prediction result between the sampling prediction reading role and the prediction probability corresponding to the sampling data and the prediction reading role and the prediction probability corresponding to all data in the user history parameters;
determining a sampling role identity parameter corresponding to a sampling prediction reading role corresponding to the sampling data according to the corresponding relation between the role and the identity, and calculating a second parameter similarity between the sampling role identity parameter and the user identity parameter;
calculating a weighted sum average value of the predicted result similarity and the second parameter similarity to obtain an accuracy parameter corresponding to the sampling data; wherein the weight of the predicted result similarity is smaller than the weight of the second parameter similarity;
And determining the sampling prediction reading role corresponding to the sampling data with the highest accuracy parameter as the reading role corresponding to the target user.
As an optional implementation manner, in the first aspect of the present invention, the selecting, according to the reading role and the user maturity, a target plot from a candidate plot database to recommend to the target user includes:
for each candidate drawing set in the candidate drawing database, calculating the character similarity between the candidate drawing set and the reading character; the candidate picture set is obtained by calculating all candidate pictures according to picture parameters of the candidate pictures in the candidate picture database through a cluster partitioning algorithm; the picture parameters comprise at least one of picture-text proportion, picture-text space, picture-text vocabulary difficulty and picture-text theme type;
determining the candidate drawing set with the highest role similarity as a target candidate drawing set;
inputting the picture parameters of each candidate picture in the target candidate picture set into a trained picture difficulty prediction model to obtain predicted picture difficulty corresponding to the candidate picture parameters; the cost difficulty prediction model is obtained through training a training data set comprising a plurality of training cost parameters and corresponding difficulty labels;
Determining a reasonable user difficulty interval corresponding to the user maturity according to a preset corresponding relation between the maturity and the difficulty;
and determining all the candidate scripts in the target candidate script set, the predicted script difficulty of which is in the reasonable user difficulty interval, as target scripts so as to be recommended to the target user.
As an optional implementation manner, in the first aspect of the present invention, the calculating a role similarity between the candidate album set and the reading role includes:
forming a first picture parameter set by picture parameters corresponding to each candidate picture in the candidate picture set;
forming a second picture parameter set by picture parameters of all pictures in all history reading records corresponding to the reading role;
calculating a parameter weight proportional to an average value of record duty ratios corresponding to the reading roles in the historical reading records corresponding to each candidate drawing in the candidate drawing set;
and calculating the set similarity between the first picture parameter set and the second picture parameter set, and calculating the product of the set similarity and the parameter weight to obtain the character similarity between the candidate picture set and the reading character.
The invention discloses a child drawing recommendation system based on role prediction, which comprises:
the acquisition module is used for acquiring user parameters of a target user, and starting equipment operation and cost drawing software operation in a historical time period; the user parameters comprise user identity parameters and user history parameters;
the first prediction module is used for predicting the reading role corresponding to the target user based on a reading role prediction algorithm model according to the user parameters of the target user;
the second prediction module is used for predicting the user maturity corresponding to the target user based on an operation maturity prediction algorithm model according to the starting equipment operation and the script software operation;
and the screening module is used for screening the target plot from the candidate plot database according to the reading role and the user maturity so as to recommend the target plot to the target user.
As an alternative embodiment, in the second aspect of the present invention, the user identity parameters include user age, user gender, user level and user physical parameters; the user history parameters include a user history sound record, a user history reading book record, a user history browsing data record, a user history focusing book record and a user history commentary book record.
As an optional implementation manner, in the second aspect of the present invention, the operation of the boot device includes at least one of a boot gesture operation, a boot key operation, a boot input password operation, and a boot browsing page operation that are made by the target user for a reading device; and/or the drawing software operation comprises at least one of an in-software browsing operation, an in-software page switching operation, an in-software selecting operation and an in-software information input operation which are made by the target user aiming at the drawing reading software.
In a second aspect of the present invention, the first prediction module predicts, based on a reading role prediction algorithm model, a specific manner of the reading role corresponding to the target user according to the user parameter of the target user, where the specific manner includes:
inputting all data in the user history parameters of the target user into a trained reading role prediction algorithm model to obtain predicted reading roles corresponding to all data in the user history parameters; the reading role prediction algorithm model is obtained through training a training data set comprising a plurality of training user history parameters and corresponding reading role labels;
Determining character identity parameters corresponding to the predicted reading characters according to the predicted reading characters and the corresponding relation between the preset characters and the identities;
calculating first parameter similarity between the character identity parameters and the user identity parameters, judging whether the first parameter similarity is larger than a first similarity threshold, and if so, determining the predicted reading character as the reading character corresponding to the target user;
if not, based on a random sampling algorithm and the reading role prediction algorithm model, re-predicting the reading role corresponding to the target user according to the user history parameters; the predicted reading role, the reading role or the reading role label comprises at least one of an adult reading role before sleeping, a child reading role before sleeping, an adult accompanying reading role, a child reading role in morning, a child reading role and a child image-text reading role.
In a second aspect of the present invention, as an optional implementation manner, the specific manner in which the first prediction module predicts the reading role corresponding to the target user again according to the user history parameter based on a random sampling algorithm and the reading role prediction algorithm model includes:
Randomly sampling data in user history parameters of the target user to obtain a plurality of sampled data, and inputting each sampled data to the reading role prediction algorithm model to obtain a sampling prediction reading role and a prediction probability corresponding to each sampled data;
calculating the similarity of the prediction result between the sampling prediction reading role and the prediction probability corresponding to the sampling data and the prediction reading role and the prediction probability corresponding to all data in the user history parameters;
determining a sampling role identity parameter corresponding to a sampling prediction reading role corresponding to the sampling data according to the corresponding relation between the role and the identity, and calculating a second parameter similarity between the sampling role identity parameter and the user identity parameter;
calculating a weighted sum average value of the predicted result similarity and the second parameter similarity to obtain an accuracy parameter corresponding to the sampling data; wherein the weight of the predicted result similarity is smaller than the weight of the second parameter similarity;
and determining the sampling prediction reading role corresponding to the sampling data with the highest accuracy parameter as the reading role corresponding to the target user.
In a second aspect of the present invention, the screening module screens the target script from a candidate script database according to the reading role and the user maturity, for recommending to the target user, including:
for each candidate drawing set in the candidate drawing database, calculating the character similarity between the candidate drawing set and the reading character; the candidate picture set is obtained by calculating all candidate pictures according to picture parameters of the candidate pictures in the candidate picture database through a cluster partitioning algorithm; the picture parameters comprise at least one of picture-text proportion, picture-text space, picture-text vocabulary difficulty and picture-text theme type;
determining the candidate drawing set with the highest role similarity as a target candidate drawing set;
inputting the picture parameters of each candidate picture in the target candidate picture set into a trained picture difficulty prediction model to obtain predicted picture difficulty corresponding to the candidate picture parameters; the cost difficulty prediction model is obtained through training a training data set comprising a plurality of training cost parameters and corresponding difficulty labels;
Determining a reasonable user difficulty interval corresponding to the user maturity according to a preset corresponding relation between the maturity and the difficulty;
and determining all the candidate scripts in the target candidate script set, the predicted script difficulty of which is in the reasonable user difficulty interval, as target scripts so as to be recommended to the target user.
In a second aspect of the present invention, as an optional implementation manner, the filtering module calculates a role similarity between the candidate album and the reading role, including:
forming a first picture parameter set by picture parameters corresponding to each candidate picture in the candidate picture set;
forming a second picture parameter set by picture parameters of all pictures in all history reading records corresponding to the reading role;
calculating a parameter weight proportional to an average value of record duty ratios corresponding to the reading roles in the historical reading records corresponding to each candidate drawing in the candidate drawing set;
and calculating the set similarity between the first picture parameter set and the second picture parameter set, and calculating the product of the set similarity and the parameter weight to obtain the character similarity between the candidate picture set and the reading character.
The third aspect of the invention discloses another child drawing recommendation system based on role prediction, which comprises:
a memory storing executable program code;
a processor coupled to the memory;
the processor calls the executable program codes stored in the memory to execute part or all of the steps in the child drawing recommendation method based on role prediction disclosed in the first aspect of the invention.
A fourth aspect of the present invention discloses a computer storage medium storing computer instructions for performing part or all of the steps of the child pictogram recommendation method based on role prediction disclosed in the first aspect of the present invention when the computer instructions are called.
Compared with the prior art, the invention has the following beneficial effects:
the invention can predict the reading role and the user maturity of the user by utilizing the user parameters and the operation of the user so as to screen out more targeted drawing to recommend, thereby comprehensively utilizing the algorithm model and the user parameters to improve the rationality and the accuracy of drawing recommendation and improving the user experience.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a child icon recommendation method based on role prediction according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a child pictorial recommendation system based on role prediction according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of another child pictogram recommendation system based on role prediction according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses a child picture recommendation method and a child picture recommendation system based on role prediction, which can predict reading roles and user maturity of users by using user parameters and operations of the users so as to screen out more targeted pictures for recommendation, thereby improving rationality and accuracy of picture recommendation by comprehensively utilizing algorithm models and user parameters and improving user experience. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a schematic flow chart of a child icon recommendation method based on role prediction according to an embodiment of the present invention. The method described in fig. 1 may be applied to a corresponding data processing device, a data processing terminal, and a data processing server, where the server may be a local server or a cloud server, and the embodiment of the present invention is not limited to the method shown in fig. 1, and the method for recommending children's drawing based on role prediction may include the following operations:
101. And acquiring user parameters of the target user, and starting up equipment operation and drawing software operation in a historical time period.
Specifically, the user parameters include a user identity parameter and a user history parameter.
102. And predicting the reading role corresponding to the target user based on the reading role prediction algorithm model according to the user parameters of the target user.
Optionally, the user identity parameters include user age, user gender, user level, and user physical parameters.
Optionally, the user history parameters include a user history sound record, a user history reading book record, a user history browsing data record, a user history focusing book record, and a user history commenting book record.
103. And predicting the user maturity corresponding to the target user based on the operation maturity prediction algorithm model according to the starting equipment operation and the drawing software operation.
Optionally, the operation of the boot device includes at least one of a boot gesture operation, a boot key operation, a boot input password operation, and a boot browsing page operation, which are performed by the target user for the reading device.
Optionally, the drawing software operation includes at least one of an in-software browsing operation, an in-software switching page operation, an in-software selecting operation and an in-software information input operation which are made by the target user for the drawing reading software.
Optionally, the operation maturity prediction algorithm model is obtained through training a training data set comprising a plurality of training user operation data and corresponding user maturity labels, and optionally, the maturity labels can be classified and labeled manually according to the age or identity of the user.
Optionally, the prediction algorithm model in the invention can be a neural network algorithm model with a CNN structure, an RNN structure or an LTSM structure.
104. And screening the objective codebook from the candidate codebook database according to the reading role and the maturity of the user so as to recommend the objective codebook to the target user.
Therefore, the method described by the embodiment of the invention can predict the reading role and the user maturity of the user by using the user parameters and the operation of the user so as to screen out more targeted drawing and recommend, thereby improving the rationality and the accuracy of drawing recommendation by comprehensively using the algorithm model and the user parameters and improving the user experience.
As an optional embodiment, in the step, according to the user parameter of the target user, based on the reading role prediction algorithm model, predicting the reading role corresponding to the target user includes:
inputting all data in the user history parameters of the target user into a trained reading role prediction algorithm model to obtain predicted reading roles corresponding to all data in the user history parameters; the reading role prediction algorithm model is obtained through training of a training data set comprising a plurality of training user history parameters and corresponding reading role labels;
Determining character identity parameters corresponding to the predicted reading characters according to the predicted reading characters and the corresponding relation between the preset characters and the identities;
calculating first parameter similarity between the character identity parameters and the user identity parameters, judging whether the first parameter similarity is larger than a first similarity threshold value, and if so, determining the predicted reading character as the reading character corresponding to the target user;
if not, based on the random sampling algorithm and the reading role prediction algorithm model, the reading role corresponding to the target user is predicted again according to the user history parameters.
Optionally, the predictive reading role, the reading role or the reading role label includes at least one of an adult pre-sleep reading role, a child pre-sleep reading role, an adult accompanying reading role, a child morning reading role, a child image reading role and a child image reading role.
Alternatively, the correspondence between roles and identities may be determined by an operator according to experiments or experience, or may be a database correspondence obtained by counting the identity data of different roles in the historical user data, for example, all the identity data corresponding to the predicted reading roles in the database correspondence may be selected to form the role identity parameters
Alternatively, the calculation of the similarity in the present invention may be implemented by a vector distance algorithm.
Through the embodiment, the roles can be predicted according to the algorithm model through the user history parameters, and the predicted roles and the identity parameters of the users are mutually verified, so that the accuracy degree of the predicted roles is improved.
As an optional embodiment, in the step, based on the random sampling algorithm and the reading role prediction algorithm model, the method predicts the reading role corresponding to the target user again according to the user history parameters, and includes:
randomly sampling data in user history parameters of a target user to obtain a plurality of sampled data, and inputting each sampled data into a reading role prediction algorithm model to obtain a sampling prediction reading role and a prediction probability corresponding to each sampled data;
for each sample data, calculating the similarity of the prediction result between the sample prediction reading role and the prediction probability corresponding to the sample data and the prediction reading role and the prediction probability corresponding to all data in the user history parameters;
determining a sampling role identity parameter corresponding to a sampling prediction reading role corresponding to the sampling data according to the corresponding relation between the roles and the identities, and calculating a second parameter similarity of the sampling role identity parameter and the user identity parameter;
Calculating a weighted sum average value of the similarity of the prediction result and the similarity of the second parameter to obtain an accuracy parameter corresponding to the sampling data; wherein the weight of the predicted result similarity is smaller than the weight of the second parameter similarity;
and determining the sampling prediction reading role corresponding to the sampling data with the highest accuracy parameter as the reading role corresponding to the target user.
By the embodiment, when the initially predicted roles have larger deviation, the random sampling algorithm is based on sampling according to the user history parameters to obtain a plurality of sampled data, and more accurate role identities are predicted based on the plurality of sampled data, because the user history parameters can have the conditions of large data quantity and poor data predictability, the random sampling is used for improving the data expression in the parameters to obtain a better prediction result, and the accuracy of role prediction can be improved.
As an alternative embodiment, in the step, according to the reading role and the maturity of the user, the method screens the objective plot from the candidate plot database to be recommended to the target user, including:
for each candidate drawing set in the candidate drawing database, calculating the character similarity between the candidate drawing set and the reading character; the candidate picture set is obtained by calculating all candidate pictures according to picture parameters of the candidate pictures in the candidate picture database through a cluster partitioning algorithm; the picture parameters comprise at least one of picture-text proportion, picture-text space, picture-text vocabulary difficulty and picture-text theme type;
Determining a candidate drawing set with highest role similarity as a target candidate drawing set;
inputting the picture parameters of each candidate picture in the target candidate picture set into a trained picture difficulty prediction model to obtain the predicted picture difficulty corresponding to the candidate picture parameters; the cost difficulty prediction model is obtained through training a training data set comprising a plurality of training cost parameters and corresponding difficulty labels;
determining a reasonable user difficulty interval corresponding to the user maturity according to a preset corresponding relation between the maturity and the difficulty;
and determining all candidate scripts of the target candidate script set, the predicted script difficulty of which is in the reasonable difficulty interval of the user, as target scripts so as to be recommended to the target user.
Alternatively, the clustering algorithm may be an algorithm model corresponding to a partitional clustering method, a hierarchical clustering method, a density clustering method or a grid clustering method, for example, may be a K-MEANS algorithm, a Gaussian Mixture Model algorithm (gaussian mixture model) or a Spectral Clustering algorithm (spectral clustering).
Optionally, the corresponding relationship between the maturity and the difficulty may be determined by an operator according to experiments or experience, specifically, when determining the corresponding relationship between the maturity and the difficulty, the operator should conform to the same standard as the maturity label in the training dataset for training the operational maturity prediction algorithm model, so that the prediction result of the operational maturity prediction algorithm model has the operability.
Through the embodiment, the target drawing book can be screened from the candidate drawing book database according to the reading role and the user maturity and based on the drawing book difficulty prediction algorithm and the difficulty interval determination rule so as to be recommended to the target user, so that the rationality and the accuracy of the drawing book recommendation can be improved by comprehensively utilizing the algorithm model and the user parameters, and the user experience is improved.
As an optional embodiment, in the step, calculating the role similarity between the candidate album set and the reading role includes:
forming a first picture parameter set by picture parameters corresponding to each candidate picture in the candidate picture set;
forming second picture parameter sets by picture parameters of all pictures in all history reading records corresponding to the reading roles;
calculating a parameter weight proportional to an average value of record duty ratios corresponding to reading roles in the history reading records corresponding to each candidate drawing in the candidate drawing set;
and calculating the set similarity between the first picture parameter set and the second picture parameter set, and calculating the product of the set similarity and the parameter weight to obtain the character similarity between the candidate picture set and the reading character.
Through the embodiment, the character similarity between the candidate picture set and the reading character can be determined by calculating the set similarity and the parameter weight, so that subsequent picture screening recommendation is facilitated, the rationality and accuracy of picture recommendation are improved, and the user experience is improved.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a child icon recommendation system based on role prediction according to an embodiment of the present invention. The system described in fig. 2 may be applied to a corresponding data processing device, a data processing terminal, and a data processing server, where the server may be a local server or a cloud server, and embodiments of the present invention are not limited. As shown in fig. 2, the system may include:
an obtaining module 201, configured to obtain user parameters of a target user, and a startup device operation and a script software operation in a historical period; the user parameters comprise user identity parameters and user history parameters;
a first prediction module 202, configured to predict, according to user parameters of a target user, a reading role corresponding to the target user based on a reading role prediction algorithm model;
the second prediction module 203 is configured to predict, according to the operation of the power-on device and the operation of the rendering software, a user maturity corresponding to the target user based on the operation maturity prediction algorithm model;
And the screening module 204 is used for screening the objective plot from the candidate plot database according to the reading role and the user maturity so as to recommend the objective plot to the target user.
As an alternative embodiment, the user identity parameters include user age, user gender, user level, and user physical parameters; the user history parameters include a user history sound record, a user history reading book record, a user history browsing data record, a user history focusing book record, and a user history commentary book record.
As an optional embodiment, the operation of the starting device includes at least one of a starting gesture operation, a starting key operation, a starting password input operation and a starting page browsing operation which are made by a target user for the reading device; and/or the drawing software operation comprises at least one of an in-software browsing operation, an in-software page switching operation, an in-software selecting operation and an in-software information input operation which are made by a target user aiming at the drawing reading software.
As an alternative embodiment, the first prediction module 202 predicts, based on the reading role prediction algorithm model, a specific manner of the reading role corresponding to the target user according to the user parameters of the target user, including:
Inputting all data in the user history parameters of the target user into a trained reading role prediction algorithm model to obtain predicted reading roles corresponding to all data in the user history parameters; the reading role prediction algorithm model is obtained through training of a training data set comprising a plurality of training user history parameters and corresponding reading role labels;
determining character identity parameters corresponding to the predicted reading characters according to the predicted reading characters and the corresponding relation between the preset characters and the identities;
calculating first parameter similarity between the character identity parameters and the user identity parameters, judging whether the first parameter similarity is larger than a first similarity threshold value, and if so, determining the predicted reading character as the reading character corresponding to the target user;
if not, based on a random sampling algorithm and a reading role prediction algorithm model, re-predicting the reading role corresponding to the target user according to the user history parameters; the predictive reading role, the reading role or the reading role label comprises at least one of an adult pre-sleep reading role, a child pre-sleep reading role, an adult accompanying reading role, a child morning reading role, a child image reading role and a child image reading role.
As an alternative embodiment, the first prediction module 202 predicts, based on the random sampling algorithm and the reading role prediction algorithm model, a specific manner of predicting the reading role corresponding to the target user according to the user history parameters, including:
randomly sampling data in user history parameters of a target user to obtain a plurality of sampled data, and inputting each sampled data into a reading role prediction algorithm model to obtain a sampling prediction reading role and a prediction probability corresponding to each sampled data;
for each sample data, calculating the similarity of the prediction result between the sample prediction reading role and the prediction probability corresponding to the sample data and the prediction reading role and the prediction probability corresponding to all data in the user history parameters;
determining a sampling role identity parameter corresponding to a sampling prediction reading role corresponding to the sampling data according to the corresponding relation between the roles and the identities, and calculating a second parameter similarity of the sampling role identity parameter and the user identity parameter;
calculating a weighted sum average value of the similarity of the prediction result and the similarity of the second parameter to obtain an accuracy parameter corresponding to the sampling data; wherein the weight of the predicted result similarity is smaller than the weight of the second parameter similarity;
And determining the sampling prediction reading role corresponding to the sampling data with the highest accuracy parameter as the reading role corresponding to the target user.
As an alternative embodiment, the filtering module 204 filters the target script from the candidate script database according to the reading role and the maturity of the user, and includes:
for each candidate drawing set in the candidate drawing database, calculating the character similarity between the candidate drawing set and the reading character; the candidate picture set is obtained by calculating all candidate pictures according to picture parameters of the candidate pictures in the candidate picture database through a cluster partitioning algorithm; the picture parameters comprise at least one of picture-text proportion, picture-text space, picture-text vocabulary difficulty and picture-text theme type;
determining a candidate drawing set with highest role similarity as a target candidate drawing set;
inputting the picture parameters of each candidate picture in the target candidate picture set into a trained picture difficulty prediction model to obtain the predicted picture difficulty corresponding to the candidate picture parameters; the cost difficulty prediction model is obtained through training a training data set comprising a plurality of training cost parameters and corresponding difficulty labels;
Determining a reasonable user difficulty interval corresponding to the user maturity according to a preset corresponding relation between the maturity and the difficulty;
and determining all candidate scripts of the target candidate script set, the predicted script difficulty of which is in the reasonable difficulty interval of the user, as target scripts so as to be recommended to the target user.
As an alternative embodiment, the specific manner of calculating the role similarity between the candidate album and the reading role by the filtering module 204 includes:
forming a first picture parameter set by picture parameters corresponding to each candidate picture in the candidate picture set;
forming second picture parameter sets by picture parameters of all pictures in all history reading records corresponding to the reading roles;
calculating a parameter weight proportional to an average value of record duty ratios corresponding to reading roles in the history reading records corresponding to each candidate drawing in the candidate drawing set;
and calculating the set similarity between the first picture parameter set and the second picture parameter set, and calculating the product of the set similarity and the parameter weight to obtain the character similarity between the candidate picture set and the reading character.
The details and technical effects of the modules in the embodiment of the present invention may refer to the description in the first embodiment, and are not described herein.
Example III
Referring to fig. 3, fig. 3 is a schematic structural diagram of another child icon recommendation system based on role prediction according to an embodiment of the present invention. As shown in fig. 3, the system may include:
a memory 301 storing executable program code;
a processor 302 coupled with the memory 301;
the processor 302 invokes the executable program code stored in the memory 301 to perform some or all of the steps in the child picture recommendation method based on role prediction disclosed in the embodiment of the present invention.
Example IV
The embodiment of the invention discloses a computer storage medium which stores computer instructions for executing part or all of the steps in the child drawing recommendation method based on role prediction disclosed in the embodiment of the invention when the computer instructions are called.
The system embodiments described above are merely illustrative, in which the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a character prediction-based children drawing recommendation method and system, which are disclosed as preferred embodiments of the invention, and are only used for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (8)
1. The children's drawing recommendation method based on role prediction is characterized by comprising the following steps:
acquiring user parameters of a target user, and starting equipment operation and drawing software operation in a historical time period; the user parameters comprise user identity parameters and user history parameters;
inputting all data in the user history parameters of the target user into a trained reading role prediction algorithm model to obtain predicted reading roles corresponding to all data in the user history parameters; the reading role prediction algorithm model is obtained through training a training data set comprising a plurality of training user history parameters and corresponding reading role labels;
Determining character identity parameters corresponding to the predicted reading characters according to the predicted reading characters and the corresponding relation between the preset characters and the identities;
calculating first parameter similarity between the character identity parameters and the user identity parameters, judging whether the first parameter similarity is larger than a first similarity threshold, and if so, determining the predicted reading character as the reading character corresponding to the target user;
if not, based on a random sampling algorithm and the reading role prediction algorithm model, re-predicting the reading role corresponding to the target user according to the user history parameters; the predicted reading role, the reading role or the reading role label comprises at least one of an adult reading role before sleeping, a child reading role before sleeping, an adult accompanying reading role, a child reading role in morning, a child reading role and a child image-text reading role;
predicting the user maturity corresponding to the target user based on an operation maturity prediction algorithm model according to the starting equipment operation and the script software operation;
for each candidate drawing set in the candidate drawing database, calculating the character similarity between the candidate drawing set and the reading character; the candidate picture set is obtained by calculating all candidate pictures according to picture parameters of the candidate pictures in the candidate picture database through a cluster partitioning algorithm; the picture parameters comprise at least one of picture-text proportion, picture-text space, picture-text vocabulary difficulty and picture-text theme type;
Determining the candidate drawing set with the highest role similarity as a target candidate drawing set;
inputting the picture parameters of each candidate picture in the target candidate picture set into a trained picture difficulty prediction model to obtain predicted picture difficulty corresponding to the candidate picture parameters; the cost difficulty prediction model is obtained through training a training data set comprising a plurality of training cost parameters and corresponding difficulty labels;
determining a reasonable user difficulty interval corresponding to the user maturity according to a preset corresponding relation between the maturity and the difficulty;
and determining all the candidate scripts in the target candidate script set, the predicted script difficulty of which is in the reasonable user difficulty interval, as target scripts so as to be recommended to the target user.
2. The character prediction based children photo recommendation method of claim 1, wherein the user identity parameters include user age, user gender, user level and user physical parameters; the user history parameters include a user history sound record, a user history reading book record, a user history browsing data record, a user history focusing book record and a user history commentary book record.
3. The character prediction-based children photo recommendation method of claim 2, wherein the boot device operation includes at least one of a boot gesture operation, a boot key operation, a boot input password operation, and a boot browsing page operation made by the target user for a reading device; and/or the drawing software operation comprises at least one of an in-software browsing operation, an in-software page switching operation, an in-software selecting operation and an in-software information input operation which are made by the target user aiming at the drawing reading software.
4. The character prediction-based children photo recommendation method of claim 1, wherein the random sampling algorithm and the reading character prediction algorithm model are used for predicting the reading character corresponding to the target user again according to the user history parameters, and the method comprises the following steps:
randomly sampling data in user history parameters of the target user to obtain a plurality of sampled data, and inputting each sampled data to the reading role prediction algorithm model to obtain a sampling prediction reading role and a prediction probability corresponding to each sampled data;
for each sample data, calculating the similarity of the prediction results between the first prediction result corresponding to the sample data and the second prediction result corresponding to all data in the user history parameters; the first prediction result comprises the sampling prediction reading role and the prediction probability; the second prediction result comprises a prediction reading role and a prediction probability corresponding to all data in the user history parameters;
Determining a sampling role identity parameter corresponding to a sampling prediction reading role corresponding to the sampling data according to the corresponding relation between the role and the identity, and calculating a second parameter similarity between the sampling role identity parameter and the user identity parameter;
calculating a weighted sum average value of the predicted result similarity and the second parameter similarity to obtain an accuracy parameter corresponding to the sampling data; wherein the weight of the predicted result similarity is smaller than the weight of the second parameter similarity;
and determining the sampling prediction reading role corresponding to the sampling data with the highest accuracy parameter as the reading role corresponding to the target user.
5. The method of claim 1, wherein calculating the similarity of roles between the candidate set of drawings and the reading role comprises:
forming a first picture parameter set by picture parameters corresponding to each candidate picture in the candidate picture set;
forming a second picture parameter set by picture parameters of all pictures in all history reading records corresponding to the reading role;
calculating a parameter weight proportional to an average value of record duty ratios corresponding to the reading roles in the historical reading records corresponding to each candidate drawing in the candidate drawing set;
And calculating the set similarity between the first picture parameter set and the second picture parameter set, and calculating the product of the set similarity and the parameter weight to obtain the character similarity between the candidate picture set and the reading character.
6. A child pictorial recommendation system based on character prediction, the system comprising:
the acquisition module is used for acquiring user parameters of a target user, and starting equipment operation and cost drawing software operation in a historical time period; the user parameters comprise user identity parameters and user history parameters;
the first prediction module is configured to predict, based on a reading role prediction algorithm model, a reading role corresponding to the target user according to a user parameter of the target user, and specifically includes:
inputting all data in the user history parameters of the target user into a trained reading role prediction algorithm model to obtain predicted reading roles corresponding to all data in the user history parameters; the reading role prediction algorithm model is obtained through training a training data set comprising a plurality of training user history parameters and corresponding reading role labels;
Determining character identity parameters corresponding to the predicted reading characters according to the predicted reading characters and the corresponding relation between the preset characters and the identities;
calculating first parameter similarity between the character identity parameters and the user identity parameters, judging whether the first parameter similarity is larger than a first similarity threshold, and if so, determining the predicted reading character as the reading character corresponding to the target user;
if not, based on a random sampling algorithm and the reading role prediction algorithm model, re-predicting the reading role corresponding to the target user according to the user history parameters; the predicted reading role, the reading role or the reading role label comprises at least one of an adult reading role before sleeping, a child reading role before sleeping, an adult accompanying reading role, a child reading role in morning, a child reading role and a child image-text reading role;
the second prediction module is used for predicting the user maturity corresponding to the target user based on an operation maturity prediction algorithm model according to the starting equipment operation and the script software operation;
the screening module is used for screening the target plot from the candidate plot database according to the reading role and the user maturity so as to recommend the target plot to the target user, and specifically comprises the following steps:
For each candidate drawing set in the candidate drawing database, calculating the character similarity between the candidate drawing set and the reading character; the candidate picture set is obtained by calculating all candidate pictures according to picture parameters of the candidate pictures in the candidate picture database through a cluster partitioning algorithm; the picture parameters comprise at least one of picture-text proportion, picture-text space, picture-text vocabulary difficulty and picture-text theme type;
determining the candidate drawing set with the highest role similarity as a target candidate drawing set;
inputting the picture parameters of each candidate picture in the target candidate picture set into a trained picture difficulty prediction model to obtain predicted picture difficulty corresponding to the candidate picture parameters; the cost difficulty prediction model is obtained through training a training data set comprising a plurality of training cost parameters and corresponding difficulty labels;
determining a reasonable user difficulty interval corresponding to the user maturity according to a preset corresponding relation between the maturity and the difficulty;
and determining all the candidate scripts in the target candidate script set, the predicted script difficulty of which is in the reasonable user difficulty interval, as target scripts so as to be recommended to the target user.
7. A child pictorial recommendation system based on character prediction, the system comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the child pictorial recommendation method based on role prediction as claimed in any of claims 1-5.
8. A computer storage medium storing computer instructions which, when invoked, are operable to perform the child picture recommendation method based on role prediction of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311207389.2A CN117194792B (en) | 2023-09-18 | 2023-09-18 | Child drawing recommendation method and system based on role prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311207389.2A CN117194792B (en) | 2023-09-18 | 2023-09-18 | Child drawing recommendation method and system based on role prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117194792A CN117194792A (en) | 2023-12-08 |
| CN117194792B true CN117194792B (en) | 2024-03-01 |
Family
ID=88995934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311207389.2A Active CN117194792B (en) | 2023-09-18 | 2023-09-18 | Child drawing recommendation method and system based on role prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117194792B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858861A (en) * | 2019-04-28 | 2020-10-30 | 华为技术有限公司 | Question-answer interaction method based on picture book and electronic equipment |
| CN113610680A (en) * | 2021-08-17 | 2021-11-05 | 山西传世科技有限公司 | AI-based interactive reading material personalized recommendation method and system |
| CN113609103A (en) * | 2021-08-17 | 2021-11-05 | 山西传世科技有限公司 | AI-based interactive reading support database construction method and system |
| US11227055B1 (en) * | 2021-07-30 | 2022-01-18 | Sailpoint Technologies, Inc. | System and method for automated access request recommendations |
| CN114117106A (en) * | 2021-12-07 | 2022-03-01 | 广州道然信息科技有限公司 | Intelligent interaction method, device, equipment and storage medium based on children's picture book |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598086B (en) * | 2018-05-25 | 2020-11-24 | 腾讯科技（深圳）有限公司 | Article recommendation method and device, computer equipment and storage medium |
| US11017452B2 (en) * | 2018-10-09 | 2021-05-25 | Dell Products L.P. | Concerted learning and multi-instance sequential prediction tree |
-
2023
- 2023-09-18 CN CN202311207389.2A patent/CN117194792B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111858861A (en) * | 2019-04-28 | 2020-10-30 | 华为技术有限公司 | Question-answer interaction method based on picture book and electronic equipment |
| US11227055B1 (en) * | 2021-07-30 | 2022-01-18 | Sailpoint Technologies, Inc. | System and method for automated access request recommendations |
| CN113610680A (en) * | 2021-08-17 | 2021-11-05 | 山西传世科技有限公司 | AI-based interactive reading material personalized recommendation method and system |
| CN113609103A (en) * | 2021-08-17 | 2021-11-05 | 山西传世科技有限公司 | AI-based interactive reading support database construction method and system |
| CN114117106A (en) * | 2021-12-07 | 2022-03-01 | 广州道然信息科技有限公司 | Intelligent interaction method, device, equipment and storage medium based on children's picture book |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117194792A (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10958748B2 (en) | Resource push method and apparatus | |
| US11042809B1 (en) | Customized predictive analytical model training | |
| CN110347872B (en) | Video cover image extraction method and device, storage medium and electronic equipment | |
| CN111966914B (en) | Content recommendation method and device based on artificial intelligence and computer equipment | |
| CN109033798B (en) | Click verification code identification method and device based on semantics | |
| CN111783712A (en) | Video processing method, device, equipment and medium | |
| CN111984821A (en) | Method and device for determining dynamic cover of video, storage medium and electronic equipment | |
| CN117235586B (en) | Hotel customer portrait construction method, system, electronic equipment and storage medium | |
| CN117409419A (en) | Image detection method, device and storage medium | |
| CN111191133A (en) | Service search processing method, device and equipment | |
| CN108520034B (en) | Application recommendation method and device and computer equipment | |
| CN113420203A (en) | Object recommendation method and device, electronic equipment and storage medium | |
| CN112330442A (en) | Modeling method and device based on ultra-long behavior sequence, terminal and storage medium | |
| CN117194792B (en) | Child drawing recommendation method and system based on role prediction | |
| JP7015927B2 (en) | Learning model application system, learning model application method, and program | |
| CN113836388A (en) | Information recommendation method and device, server and storage medium | |
| CN112492397A (en) | Video processing method, computer device, and storage medium | |
| CN114328995A (en) | Content recommendation method, device, equipment and storage medium | |
| CN111127057B (en) | Multi-dimensional user portrait recovery method | |
| CN117217624B (en) | Child reading level prediction method and system based on drawing book reading record | |
| CN114511095A (en) | Data processing method and device, computing equipment and storage medium | |
| CN112463964A (en) | Text classification and model training method, device, equipment and storage medium | |
| CN111915339A (en) | Data processing method, device and equipment | |
| CN112925972B (en) | Information pushing method, device, electronic equipment and storage medium | |
| CN110597965B (en) | Emotion polarity analysis method and device for article, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |