CN110083687B - Information conversion method, equipment and storage medium - Google Patents
Information conversion method, equipment and storage medium Download PDFInfo
- Publication number
- CN110083687B CN110083687B CN201910351573.1A CN201910351573A CN110083687B CN 110083687 B CN110083687 B CN 110083687B CN 201910351573 A CN201910351573 A CN 201910351573A CN 110083687 B CN110083687 B CN 110083687B
- Authority
- CN
- China
- Prior art keywords
- user
- target
- information
- corpus
- conversion
- 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
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 199
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012216 screening Methods 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 230000001174 ascending effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000001915 proofreading effect Effects 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims 1
- 238000004891 communication Methods 0.000 abstract description 30
- 230000001965 increasing effect Effects 0.000 abstract description 9
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 10
- 230000014509 gene expression Effects 0.000 description 5
- 238000011426 transformation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002716 delivery method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
The application discloses an information conversion method, information conversion equipment and a storage medium, and relates to the technical field of information processing. The method comprises the following steps: the method comprises the steps that a first terminal responds to input operation of a first user, obtains input information to be sent to a second user by the first user, and obtains a target conversion type of the input information; determining conversion information of the input information according to the acquired target conversion type and the corpus; and sending the conversion information to the second terminal so that the second terminal displays the conversion information to the second user. In the technical scheme, the first terminal sends the conversion information to the second terminal after converting the input information input by the first user, so that the conversion information displayed by the second terminal to the second user is more in line with the personality, characteristics, habits and the like of the second user, the comfort and the smoothness of the chat between the first user and the second user can be improved, the communication pleasure of the two users can be promoted, and meanwhile, the communication pleasure can be increased.
Description
Technical Field
The present application relates to the field of information processing technologies, and in particular, to an information conversion method, an information conversion device, and a storage medium.
Background
With the rapid development of internet technology and the popularization of mobile terminal devices such as mobile phones, information transmission through social software has become one of the main ways for people to communicate with each other. Currently, the information delivery method in the social software is usually that the sender inputs information according to the sentence pattern, word help and other methods that the sender is accustomed to, and the information input by the sender is directly displayed to the receiver. However, when the sending party and the receiving party are different in age, character, education level, geographical location, etc., the sentence patterns, the word help words, the popular vocabulary, etc. often adopted are very different, which is not favorable for enhancing the communication quality of the two parties, and also affects the fluency of the communication between the two parties.
Disclosure of Invention
It is a primary object of the present application to provide an information conversion method, apparatus and storage medium, which are intended to solve the above technical problems at least to a first extent.
In order to achieve the above object, a first aspect of the present application provides an information conversion method applied to a first terminal, including:
responding to the input operation of a first user, and acquiring input information to be sent to a second user by the first user;
acquiring a target conversion type of the input information;
determining conversion information of the input information according to the target conversion type and the corpus;
and sending the conversion information to a second terminal so that the second terminal displays the conversion information to the second user.
In order to achieve the above object, a second aspect of the present application provides an information conversion method, applied to a server, including:
acquiring user data and public data;
and training the user data and the public data to obtain a corpus so as to enable the terminal to download the corpus, and determining conversion information of the user input information according to the corpus.
To achieve the above object, a third aspect of the present application provides an electronic device comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing when executing the computer program to implement the method according to the first or second aspect of the application.
To achieve the above object, a fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method as described in the first or second aspect of the present application.
According to the technical scheme, when the first user and the second user carry out information communication through social software, the first terminal obtains the target conversion type of the input information input by the first user, and sends the conversion information to the second terminal after converting the input information input by the first user, so that the conversion information displayed to the second user by the second terminal is more in line with the character, characteristics, habits and the like of the second user, the comfort and the fluency of chatting between the first user and the second user can be improved, the communication interest of the two users can be improved, and meanwhile, the communication interest can be increased.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of an information transformation method provided in some embodiments of the present application;
FIG. 2 is a schematic diagram of an information transformation method provided in some embodiments of the present application;
FIG. 3 is a flow chart of an information transformation method provided in some embodiments of the present application;
fig. 4 is a schematic structural diagram of an information conversion apparatus according to some embodiments of the present application;
FIG. 5 is a schematic diagram of another information transformation apparatus according to some embodiments of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to some embodiments of the present application.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which this application belongs.
Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The embodiment of the present application is mainly directed to the problem in the related art that, when users communicate with each other through social software, a terminal (hereinafter, referred to as a first terminal) of a sender (hereinafter, referred to as a first user) directly transmits input information of the first user to a terminal (hereinafter, referred to as a second terminal) of a receiver (hereinafter, referred to as a second user), and the input information of the first user and the input information of the second user may adopt different sentences and vocabularies due to differences in ages, characters and the like between the first user and the second user, which is not favorable for improving the communication quality of the two users and also affects the smoothness of communication between the two users.
Therefore, in the embodiment of the application, the first terminal obtains the target conversion type of the input information of the first user, converts the input information input by the first user and then sends the converted information to the second terminal, so that the converted information displayed to the second user by the second terminal is more in line with the personality, characteristics, habits and the like of the second user, the comfort and the fluency of the chat between the first user and the second user can be improved, the communication pleasure of the two users can be promoted, and the communication pleasure can be increased.
The information conversion method, apparatus, and storage medium provided by the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flowchart of an information transformation method provided in some embodiments of the present application, applied to a first terminal, as shown in fig. 1, including:
step 101: responding to the input operation of a first user, and acquiring input information to be sent to a second user by the first user;
step 102: acquiring a target conversion type of input information;
in some embodiments of the present application, step 102 may further include, before: accessing a preset storage area, downloading a corpus stored in the preset storage area and storing the corpus locally; the corpus is obtained by acquiring a large amount of user data, a dialect library, an expression package and other public data for a server side and training the acquired data; the corpus comprises associations of conversion types and labels, and associations of labels and linguistic materials, and one conversion type can be associated with one or more labels, and one label can be associated with one or more linguistic materials; the tags are used for describing the characteristics of the user, and the language material associated with each tag is favorite, habit, common sentence pattern, picture, expression and the like of the user with the characteristics described by the tags. The preset storage area can be a cloud storage area and can also be a storage area of a server side. By downloading the corpus in the preset storage area, when the input information to be sent to the second user by the first user is acquired, the conversion information of the input information is determined according to the corpus.
In some embodiments of the application, after the first terminal is started, the first terminal may monitor a trigger event that the session box is opened in real time, and when the trigger event is monitored, display at least one preset conversion type in the session box opened by the first user, and obtain a target conversion type selected by the first user in the displayed at least one conversion type; wherein, the preset at least one conversion type is a conversion type included in the corpus.
For example, the preset conversion type is displayed to include a foreign language background, a web popularity, a Sichuan dialect, and the like, and the conversion type selected by the first user is acquired as the foreign language background, and then the foreign language background is used as the target conversion type.
Therefore, the preset conversion type is displayed for the first user, so that the first user can be reminded to select the conversion type, the first user can select the proper conversion type according to the character, the characteristic, the habit and the like of the second user, the comfort and the fluency of chatting with the second user are further improved, the communication pleasure of the two users is promoted, and the communication pleasure can be increased.
In other embodiments of the present application, after the first terminal is started, the first terminal may monitor a trigger event that the dialog box is opened in real time, determine a second user corresponding to the dialog box when the trigger event is monitored, send a display request to the second terminal of the second user, display at least one preset conversion type to the second user through the second terminal, and obtain a target conversion type selected by the second user among the displayed at least one conversion type; wherein, the preset at least one conversion type is a conversion type included in the corpus.
Specifically, when the second terminal receives a display request of the first terminal, displaying at least one preset conversion type; the second terminal receives a target conversion type selected by the second user in the displayed at least one conversion type and sends the target conversion type to the first terminal; and the first terminal receives the target conversion type sent by the second terminal.
Therefore, the preset conversion type is displayed for the second user to select, so that the target conversion type is more in line with the requirement of the second user and more accurate; and the comfort and the fluency of the chat between the first user and the second user can be further improved, the communication pleasure of the two parties can be improved, and the communication pleasure can be increased.
In other embodiments of the present application, after the first terminal is started, the first terminal may monitor a trigger event that the dialog box is opened in real time, and when the trigger event is monitored, obtain user information of a second user corresponding to the opened dialog box, and determine a target conversion type of the input information according to the obtained user information.
In some embodiments of the present application, determining the target conversion type of the input information according to the acquired user information may include: generating a user label according to the acquired user information; determining a target conversion type of input information according to the user label and the incidence relation between the label and the conversion type; specifically, a user label is generated according to the information such as age, occupation, native place and the like contained in the user information; and acquiring a conversion type associated with the user label from the association relationship between the label and the conversion type included in the corpus, and taking the acquired conversion type as a target conversion type. For example, the user information includes "native through Sichuan", the generated tag may include "Sichuan", the conversion type associated with obtaining "Sichuan" includes a Sichuan dialect, and the Sichuan dialect is used as a target conversion type of the input information. Therefore, the first terminal can automatically convert the input information of the first user into the conversion information suitable for the characters, characteristics and the like of the second user by acquiring the user information of the second user and determining the target conversion type, and particularly under the condition that the first user and the second user are not familiar enough, the first terminal not only can improve the comfort and the fluency of the chat between the first user and the second user, but also is beneficial to improving the good communication between the first user and the second user and increasing the communication pleasure.
In further embodiments of the present application, determining the target conversion type of the input information according to the acquired user information may include: generating a user label according to the acquired user information; determining at least one recommended conversion type according to the user label and the incidence relation between the label and the conversion type; and displaying the determined at least one recommended conversion type, and acquiring a target conversion type selected by the first user or the second user in the displayed recommended conversion types. Specifically, the first terminal generates a user label according to information such as age, occupation, native place and the like contained in the user information; and acquiring a conversion type associated with the user label in the association relationship between the label and the conversion type included in the corpus, displaying the acquired conversion type as a recommended conversion type to the first user, and taking the recommended conversion type selected by the first user as a target conversion type. Or after the first terminal acquires the conversion types associated with the user tags, the acquired conversion types are used as recommended conversion types, a display request is sent to the second terminal, and the target conversion types selected by the second user in the recommended conversion types are received through the second terminal. In the method, the first terminal automatically determines the conversion type suitable for the second user according to the user label by acquiring the user information of the second user and generating the user label, and displays the conversion type so that the first user or the second user can select the optimal conversion type which is closer to the character and the characteristic of the second user, so that the comfort and the fluency of the chat between the first user and the second user can be improved, the communication interest of the two parties can be improved, and the communication interest can be increased.
Step 103: determining conversion information of the input information according to the target conversion type and the corpus;
wherein the conversion information includes at least one of text, picture, and expression.
In some embodiments of the present application, step 103 may comprise:
step 103-1: determining at least one target label according to the determined target conversion type;
specifically, when the first terminal displays at least one preset conversion type and receives a target conversion type selected by a first user or a second user, obtaining a label corresponding to the target conversion type from an incidence relation between the conversion type and the label included in the corpus and taking the label as the target label; when the first terminal acquires the user information of the second user and generates a user tag, and the target conversion type is automatically determined according to the user tag, the generated user tag can be used as a target tag; when the first terminal acquires the user information of the second user and generates a user label, and then the recommended conversion type is displayed, and the target conversion type selected by the first user or the second user is received, the label corresponding to the target conversion type is acquired in the incidence relation between the conversion type and the label included in the corpus and is used as the target label.
For example, the object conversion type is "foreign language background", and the object label is "foreign enterprise and study"
Step 103-2: searching at least one language material matched with the input information in the corpus according to the target label;
in some implementations of the present application, step 103-2 may include: searching language materials related to the target label in the corpus, and searching language materials with the same meaning as the input information in the searched language materials as language materials matched with the input information;
for example, the input information is "food material is fresh", the language material for which the meaning of the input information "food material is fresh" is searched for as "food must flash" in the searched language material according to the target label "forensics and study", and the like, including "how your body is OK", "Tomorrow i has an assignment to die", "food must flash", and the like, and the "food must flash" is used as the language material matched with the input information.
In other implementations of the present application, step 103-2 may include: and searching candidate language materials with the same meaning as the input information in the corpus, comparing the labels associated with the candidate language materials with the target labels, and taking the candidate language materials associated with the labels which are successfully compared as the language materials matched with the input information.
For example, the input information is "food material is fresh", candidate language materials which have the same meaning as the input information are searched in the corpus and comprise "fresh food", "food material needs to be in a quality guarantee period", "food must be flashed", and the like, and the label associated with the "fresh food" is "youth and doctor", "food material needs to be in a quality guarantee period", the label associated with the "food material needs to be in a quality guarantee period" is "doctor and consumer", and the label associated with the "food must be flashed" is "foreign enterprise and study"; and comparing the tags associated with the searched candidate language materials with the target tags in sequence, and taking the tags 'foreign enterprises and reservation' associated 'food must flash' which are successfully compared as the language materials matched with the input information.
The method comprises the steps of searching at least one language material matched with input information in a corpus, and screening conversion information of the input information from the matched at least one language material subsequently.
Step 103-3: and screening the target language material from the matched at least one language material, and determining the target language material as conversion information of the input information.
Specifically, according to the weight of each matched language material relative to each target label, the first matching weight of each matched language material relative to all target labels is respectively calculated; and screening the target language material in the matched at least one language material according to the first matching weight.
In this embodiment, the corpus further includes a weight of each linguistic material relative to each label, which is used to represent the usage heat of the linguistic material relative to the label; for example, the language material "food must flash" has a weight of 0.8 with respect to label outsiders, a weight of 0.8 with respect to label study, a weight of 0.2 with respect to label doctors, and a heat of 0.1 with respect to label elderly people. Therefore, by calculating the first matching weight of each matched language material with respect to all the target tags, the usage heat of each matched language material with respect to all the tags can be determined, and thus the target language material can be determined according to the usage heat.
Further, the first matching weight may be calculated as P ═ Y × W1+ Y × W2+ Y × W3+ … + Y × Wn, where P is the first matching weight, Y is the language material, W1, W2, and W3 … Wn are weights of the language material Y relative to target tag 1, target tag 2, and target tag 3 …, target tag n, where n is the number of target tags.
In some embodiments of the present application, the screening the matched at least one language material for the target language material according to the first matching weight may include:
step A1: selecting a first matching weight larger than a preset weight from the first matching weights, and taking the first matching weight as a second matching weight;
specifically, the first matching weight of each matched linguistic material is compared with a preset weight, and the first matching weight larger than the preset weight is used as a second matching weight.
Step A2: determining that the number of the second matching weights is unique, and taking the language material corresponding to the second matching weights as a target language material;
in some embodiments of the present application, step a2 may be preceded by: judging the type of the number of the second matching weights, if the number of the second matching weights is one, executing step a2, if the number of the second matching weights is greater than one, executing step A3, and if the number of the second matching weights is zero, executing step a 4.
Step A3: selecting the largest second matching weight from the second matching weights, and taking the language material corresponding to the selected largest second matching weight as the target language material; or displaying the language materials corresponding to the second matching weight, and receiving the target language materials selected by the first user in the language materials corresponding to the second matching weight;
in some embodiments of the present application, it is determined that the number of the second matching weights is not one, the second matching weights may be ranked to obtain a largest second matching weight, and the language material corresponding to the largest second matching weight is used as the target language material;
in other embodiments of the present application, it is determined that the number of the second matching weights is not one, and the language material corresponding to the second matching weights may also be displayed, and the target language material selected by the first user may be received.
Further, displaying the language material corresponding to the second matching weight may further include: determining that the number of the second matching weights is not more than the first preset number, and displaying language materials corresponding to the second matching weights; and determining that the number of the second matching weights is larger than the first preset number, sequencing the second matching weights in a descending or ascending manner, selecting the second matching weights which are arranged in front of or behind the sequence of the first preset number in the sequencing result, and displaying the language material corresponding to the selected second matching weights. For example, the first preset number is 3, the number of the second matching weights is 5, the second matching weights are sorted in a descending order, and the second matching weights located in the first three positions in the sorting result are displayed. Therefore, only the language materials corresponding to the first preset number and the larger second matching weight are displayed, so that the language materials with high use heat can be displayed to the first user, the first user does not need to check and select from too many language materials one by one, and the selection difficulty of the first user is reduced.
Step A4: and determining the number of the second matching weights to be zero, displaying the language materials corresponding to the first matching weights, and receiving the target language materials selected by the first user from the language materials corresponding to the first matching weights.
Specifically, judging whether the number of the first matching weights is not more than a second preset number, and displaying language materials corresponding to the first matching weights when the number of the first matching weights is not more than the second preset number; and when the number of the first matching weights is determined to be larger than a second preset number, sorting the first matching weights in a descending or ascending manner, selecting the first matching weights which are arranged in front of or behind the second preset number in the sorting result, and displaying the language material corresponding to the selected first matching weights. Therefore, only the language materials corresponding to the second preset number and the larger first matching weight are displayed, so that the language materials with higher use heat can be displayed to the first user, the first user does not need to check and select too many language materials one by one, and the selection difficulty of the first user is reduced.
It should be noted that the first preset number and the second preset number may be the same or different, and may be set according to the needs in practical applications.
In other embodiments of the present application, step 103-3 may further be:
step 103-3': and screening target language materials from the at least one matched language material, and if the input information is the same as the target language materials or the similarity between the input information and the target language materials meets a similarity threshold, determining the input information as conversion information.
Specifically, the target language material is screened from the at least one matched language material, whether the target language material is the same as the input information or not is judged, if the judgment result is yes, the input information is determined to be conversion information, and if the judgment result is no, the target language material is determined to be conversion information. Or calculating the similarity between the input information and the target language material, comparing the calculated similarity with a similarity threshold, if the calculated similarity is not less than the similarity threshold, determining the input information as conversion information, and if the calculated similarity is less than the similarity threshold, determining the target language material as conversion information.
The method for calculating the similarity may be set in practical application as needed, and the present application is not limited specifically. For example, the calculation may be performed based on the number of characters included in the input information and the target language material. By determining the input information as the conversion information, the first user can determine that the language habit of the first user is similar to that of the second user, and the communication enthusiasm of the first user and the second user can be improved.
Therefore, the determination of the conversion information of the input information is completed, and the conversion information to be sent to the second terminal is ensured to be more in line with the character, characteristics, habits and the like of the second user.
Step 104: and sending the conversion information to the second terminal so that the second terminal displays the conversion information to the second user.
For example, the target conversion type is a foreign language background, the input information is 'food material is fresh', and the conversion information 'food must flash' is sent to the second terminal; for another example, the target conversion type is network popularity, the input information is "good and severe", and the conversion information "bow" is sent to the second terminal; as another example, the target conversion type is a character, the input information is "refuel", and the conversion information is sent
To the second terminal; as another example, the target conversion type is the sikawa dialect, and the input information is "what? ", send the conversion information" what? "to the second terminal.
Based on any of the above embodiments, in some embodiments of the present application, the method further comprises: and accessing the preset storage area at preset time intervals, determining that the new version of the corpus is stored in the preset storage area, deleting the currently locally stored corpus, and downloading the new version of the corpus to be stored locally.
Specifically, the first terminal accesses the preset storage area at preset time intervals, judges whether version information of a corpus stored in the preset storage area is the same as version information of a locally stored corpus, deletes the currently locally stored corpus when the version information of the corpus stored in the preset storage area is different from the version information of the locally stored corpus, and downloads a new version of the corpus stored in the preset storage area to be stored locally. The preset time can be 10 days, 15 days and the like, and can be set automatically according to needs in practical application. By regularly updating the corpus, the timeliness of the corpus can be ensured, so that the conversion information of the input information is more consistent with the customary sentence pattern of the current user.
Referring to fig. 2, based on the information conversion method provided in the foregoing embodiment, in a specific application scenario, the first terminal first obtains input information of the first user in response to an input operation of the first user; then, carrying out information conversion operation on the input information, and in the information conversion process, firstly acquiring a target conversion type of the input information, and determining at least one target label according to the target conversion type; searching matched language materials according to the target tags, and screening target language materials with the same meaning as the input information from the matched language materials; judging whether the target language material is the same as the input information or not, and if so, sending the input information to a second terminal, and displaying the input information by the second terminal; and when the judgment result is negative, the target language material is used as the conversion information of the input information and is sent, the conversion information is sent to the second terminal, and the second terminal displays the conversion information.
Therefore, when the first user and the second user carry out information communication through social software, the first terminal obtains the target conversion type of the input information input by the first user, converts the input information input by the first user and then sends the converted information to the second terminal, so that the converted information displayed by the second terminal to the second user is more in line with the personality, characteristics, habits and the like of the second user, the comfort and the fluency of the chat between the first user and the second user can be improved, the communication pleasure of the two users can be promoted, and meanwhile, the communication pleasure can be increased.
Fig. 3 is a flowchart of an information transformation method provided in some embodiments of the present application, applied to a server, as shown in fig. 3, including:
step 201: acquiring user data and public data;
specifically, user data is obtained from a user information base, and public data in the current network is obtained; the user data may include personal information of the user, such as age, occupation, location, and the like, and the user data may also include a history chat record of the user; public data includes dialect libraries, color and text libraries, emoticons, and the like. It should be noted that the user data does not include personal privacy data of the user, such as user identification, so that the obtained user data is no longer associated with each specific user, and a corpus applicable to all users is obtained after training.
Step 202: training the acquired user data and public data to obtain a corpus so that the terminal can determine conversion information of the user input information according to the corpus.
Training the user data and the public data to obtain the corpus may include: preprocessing the acquired user data and public data, and training the preprocessed data to obtain a corpus; the preprocessing may include at least one of word collation, text classification, syntactic analysis, automatic word segmentation, part-of-speech tagging; the training process may be any one of the existing training modes such as text and pictures, for example, deep neural network training, for which, the present application is not specifically limited and detailed in the embodiment of the present application for the specific training process, and the present training process is referred to.
The corpus in the embodiment of the application comprises an incidence relation between a conversion type and a label and an incidence relation between the label and language material, wherein one conversion type can be associated with one or more labels, and one label can be associated with one or more language materials; the tags are used for describing features of the user, and language materials associated with each tag are favorite, habit, common sentence patterns, pictures, expressions and the like of the user with the features described by the tags.
In some embodiments of the present application, the method further comprises: and storing the corpus into a preset storage area, updating the corpus at preset intervals, and storing the updated corpus of a new version into the preset storage area so that the terminal can download the corpus in the preset storage area. The preset storage area can be a cloud storage area and can also be a local storage area of the server. The preset time can be 10 days, 15 days and the like, and can be set automatically according to the needs in practical application. By regularly updating the corpus, the timeliness of the corpus can be ensured, so that the conversion information obtained by converting the input information by the terminal is more in line with the customary sentence pattern of the current user. The process of updating the corpus is the same as the process described in step 201 and step 202, and is not described herein again.
Therefore, the server acquires a large amount of user data, a dialect library, an expression package and other public data, trains the acquired data to obtain a corpus for the terminal to download, so that the terminal can acquire a target conversion type of the input information input by the first user, converts the input information of the first user and then sends the converted information to the second terminal, the converted information displayed by the second terminal to the second user is more in line with the personality, characteristics, habits and the like of the second user, the comfort and the fluency of the chat between the first user and the second user can be improved, the communication interest of the two parties can be improved, and meanwhile, the communication interest can be increased.
The above is an information conversion method provided in the embodiments of the present application, and corresponding to the above method, the present invention also provides an information conversion apparatus, and since an implementation scheme for solving the problem of the apparatus is similar to the above method, corresponding contents to the method part may refer to the detailed description of the above method embodiments, and will not be described in detail later. It is understood that the apparatus provided in the present application may include a unit or a module capable of performing each step of the above method examples, and the unit or the module may be implemented by hardware, software or a combination of hardware and software, and the present invention is not limited thereto. The following description is made with reference to fig. 4 and 5.
Fig. 4 is a schematic structural diagram of an information conversion apparatus according to some embodiments of the present application, and as shown in fig. 4, the information conversion apparatus 30 includes:
a first obtaining module 301, configured to obtain, in response to an input operation of a first user, input information to be sent to a second user by the first user;
a second obtaining module 302, configured to obtain a target conversion type of the input information;
a determining module 303, configured to determine conversion information of the input information according to the target conversion type and the corpus;
a sending module 304, configured to send the conversion information to the second terminal, so that the second terminal displays the conversion information to the second user.
In some embodiments of the present application, the second obtaining module 302 may be specifically configured to:
displaying at least one preset conversion type, and acquiring a target conversion type selected by a first user or a second user in the at least one conversion type;
in other embodiments of the present application, the second obtaining module 302 may be specifically configured to:
and acquiring user information of a second user, and determining the target conversion type of the input information according to the user information.
Further, the second obtaining module 302 is configured to:
generating a user label according to the user information;
determining a target conversion type of input information according to the user label and the incidence relation between the label and the conversion type; or,
determining at least one recommended conversion type according to the user label and the incidence relation between the label and the conversion type; and displaying the determined at least one recommended conversion type, and acquiring a target conversion type selected by the first user or the second user in the at least one recommended conversion type.
In some embodiments of the present application, the determining module 303 may include:
the determining submodule is used for determining at least one target label according to the target conversion type;
the searching sub-module is used for searching at least one language material matched with the input information in the corpus according to the target label;
the screening submodule is used for screening the target language material from the at least one matched language material and taking the target language material as the conversion information of the input information; or screening target language materials from the at least one matched language material, and if the input information is the same as the target language materials or the similarity between the input information and the target language materials meets a similarity threshold, determining the input information as conversion information.
In some embodiments of the present application, the sending module 304 is further configured to:
and determining that the target language material is the same as the input information, and sending the input information to the second terminal so that the second terminal displays the input information to the second user.
In some embodiments of the present application, the lookup submodule may be specifically configured to:
searching language materials related to the target label in a corpus, and searching language materials with the same meaning as the input information in the language materials related to the target label as language materials matched with the input information;
in other embodiments of the present application, the lookup submodule may be specifically configured to:
and searching candidate language materials with the same meaning as the input information in a corpus, comparing labels associated with the candidate language materials with target labels, and taking the candidate language materials associated with the labels which are successfully compared as the language materials matched with the input information.
In some embodiments of the present application, the screening submodule may include:
the calculation unit is used for respectively calculating the first matching weight of each matched language material relative to all the target labels according to the weight of each matched language material relative to each target label;
and the screening unit is used for screening the target language material in the matched at least one language material according to the first matching weight.
In some embodiments of the present application, the screening unit may be specifically configured to:
selecting a first matching weight larger than a preset weight from the first matching weights, and taking the first matching weight as a second matching weight;
determining the number of the second matching weights as one, and taking the language material corresponding to the second matching weights as a target language material;
determining that the number of the second matching weights is larger than one, selecting the largest second matching weight from the second matching weights, and taking the language material corresponding to the largest second matching weight as the target language material; or displaying the language materials corresponding to the second matching weight, and receiving the target language materials selected by the first user in the language materials corresponding to the second matching weight;
and determining the number of the second matching weights to be zero, displaying the language materials corresponding to the first matching weights, and receiving the target language materials selected by the first user from the language materials corresponding to the first matching weights.
Further, the screening submodule may be specifically configured to:
determining that the number of the second matching weights is not more than the first preset number, and displaying language materials corresponding to the second matching weights;
and determining that the number of the second matching weights is larger than the first preset number, sequencing the second matching weights in a descending or ascending manner, selecting the second matching weights which are arranged in front of or behind the sequence of the first preset number in the sequencing result, and displaying the language material corresponding to the selected second matching weights.
Further, the screening submodule may be further specifically configured to:
determining that the number of the first matching weights is not more than a second preset number, and displaying language materials corresponding to the first matching weights;
and determining that the number of the first matching weights is larger than a second preset number, sequencing the first matching weights in a descending or ascending manner, selecting the first matching weights which are in front of or behind the sequencing of the second preset number in the sequencing result, and displaying the language material corresponding to the selected first matching weights.
Based on any one of the above embodiments, in some embodiments of the present application, the apparatus may further include:
and the downloading module is used for accessing the preset storage area, downloading the corpus in the preset storage area and storing the corpus to the local, wherein the preset storage area is a cloud storage area or a storage area of a server side.
In some embodiments of the present application, the downloading module may be specifically configured to:
accessing a preset storage area at preset time intervals;
determining that a new version of a corpus is stored in a preset storage area;
and deleting the currently locally stored corpus, and downloading the new version corpus to be stored locally.
Fig. 5 is a schematic structural diagram of an information conversion apparatus according to some embodiments of the present application, and as shown in fig. 5, the information conversion apparatus 40 includes:
an obtaining module 401, configured to obtain user data and public data;
the training module 402 is configured to train user data and public data to obtain a corpus, so that the terminal can download the corpus, and determine conversion information of user input information according to the corpus.
In some embodiments of the present application, the training module 402 may be specifically configured to:
preprocessing user data and public data, wherein the preprocessing comprises at least one of character proofreading, text classification, syntactic analysis, automatic word segmentation and part of speech tagging;
and training the preprocessed data to obtain a corpus.
In some embodiments of the present application, the apparatus may further comprise:
the storage module is used for storing the corpus to a preset storage area so that a terminal can download the corpus in the preset storage area;
the updating module is used for updating the corpus every preset time;
and the storage module is also used for storing the updated corpus of the new version into a preset storage area.
The device identification apparatus provided in the embodiment of the present application has the same effect as the device identification method provided in the foregoing embodiment, based on the same inventive concept.
The embodiment of the present application further provides an electronic device corresponding to the information conversion method provided in the foregoing embodiment, where the electronic device may be an electronic device for a server, such as a server, and includes an independent server, a distributed server cluster, and the like, so as to execute the information conversion method applied to the server; the electronic device may also be an electronic device for a terminal, such as a mobile phone, a notebook computer, a tablet computer, a desktop computer, etc., to execute the above information conversion method applied to the terminal.
Fig. 6 is a schematic diagram of an electronic device according to some embodiments of the present application. As shown in fig. 6, the electronic apparatus 50 includes: memory 501, processor 502, bus 503, and communication interface 504; the memory 501, the processor 502 and the communication interface 504 are connected by a bus 503; the memory 501 stores a computer program that can be executed on the processor 502, and when the processor 502 executes the computer program, the information conversion method applied to the terminal or the information conversion method applied to the server, which are provided by any of the foregoing embodiments of the present application, are executed.
The Memory 501 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The processor 502 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 502. The Processor 502 may also be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
The bus 503 may be an ISA (English: Industry Standard Architecture; Chinese: Industry Standard Architecture) bus, a PCI (English: Peripheral Component Interconnect; Chinese: Peripheral Component Interconnect) bus, an EISA (English: Extended Industry Standard Architecture; Chinese: Extended Industry Standard Architecture) bus, or the like.
The electronic device provided by the embodiment of the application and the information conversion method provided by the embodiment of the application have the same inventive concept and have the same beneficial effects as the method adopted, operated or realized by the electronic device.
The present embodiment also provides a computer readable medium corresponding to the information conversion method provided by the foregoing embodiment, and a computer program (i.e., a program product) is stored thereon, and when being executed by a processor, the computer program executes the information conversion method applied to the terminal or the information conversion method applied to the server side provided by any of the foregoing embodiments.
The computer-readable storage medium includes, but is not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memories (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical and magnetic storage media, which are not described in detail herein.
The computer-readable storage medium provided by the above-mentioned embodiments of the present application and the information conversion method provided by the embodiments of the present application have the same beneficial effects as the method adopted, executed or implemented by the application program stored in the computer-readable storage medium.
It should be noted that 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 application. 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.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present disclosure, and the present disclosure should be construed as being covered by the claims and the specification.
Claims (9)
1. An information conversion method is applied to a first terminal, and is characterized by comprising the following steps:
responding to the input operation of a first user, and acquiring input information to be sent to a second user by the first user;
acquiring a target conversion type of the input information; the method comprises the following steps: displaying at least one preset conversion type, and acquiring a target conversion type selected by the first user or the second user in the at least one conversion type; or acquiring user information of the second user, and determining a target conversion type of the input information according to the user information;
determining conversion information of the input information according to the target conversion type and the corpus; sending the conversion information to a second terminal so that the second terminal displays the conversion information to the second user;
wherein determining the target conversion type of the input information according to the user information comprises: generating a user label according to the user information;
determining a target conversion type of the input information according to the user tag and the incidence relation between the tag and the conversion type; or,
determining at least one recommended conversion type according to the user label and the incidence relation between the label and the conversion type; displaying the at least one recommended conversion type, and acquiring a target conversion type selected by the first user or the second user in the at least one recommended conversion type;
wherein the determining the conversion information of the input information according to the target conversion type and the corpus comprises:
determining at least one target label according to the target conversion type;
searching at least one language material matched with the input information in the corpus according to the target label;
screening target language materials from the matched at least one language material, and determining the target language materials as conversion information of the input information; or,
screening target language materials from the at least one matched language material, and if the input information is the same as the target language materials or the similarity between the input information and the target language materials meets a similarity threshold, determining the input information as the conversion information;
the screening of the matched at least one language material for target language material comprises: respectively calculating the first matching weight of each matched language material relative to all target labels according to the weight of each matched language material relative to each target label; screening the target language material from the matched at least one language material according to the first matching weight; the screening the target language material in the matched at least one language material according to the first matching weight comprises: selecting a first matching weight which is larger than a preset weight from the first matching weights, and taking the first matching weight as a second matching weight; determining the number of the second matching weights to be one, and taking the language material corresponding to the second matching weights as the target language material; determining that the number of the second matching weights is larger than one, selecting the largest second matching weight from the second matching weights, and taking the language material corresponding to the largest second matching weight as the target language material; or, displaying the language materials corresponding to the second matching weight, and receiving the target language materials selected by the first user in the language materials corresponding to the second matching weight; determining the number of the second matching weights to be zero, displaying language materials corresponding to the first matching weights, and receiving the target language materials selected by the first user in the language materials corresponding to the first matching weights;
the displaying the language material corresponding to the second matching weight includes: determining that the number of the second matching weights is not more than a first preset number, and displaying language materials corresponding to the second matching weights; determining that the number of the second matching weights is larger than a first preset number, sorting the second matching weights in a descending order or an ascending order, selecting the second matching weights which are arranged in front of or behind the first preset number in a sorting result, and displaying language materials corresponding to the selected second matching weights;
the displaying the language material corresponding to the first matching weight comprises: determining that the number of the first matching weights is not more than a second preset number, and displaying language materials corresponding to the first matching weights; and determining that the number of the first matching weights is larger than a second preset number, sequencing the first matching weights in a descending or ascending manner, selecting the first matching weights which are arranged in front of or behind the second preset number in the sequencing result, and displaying the language material corresponding to the selected first matching weights.
2. The method of claim 1, wherein the searching the corpus for at least one linguistic material matching the input information according to the target label comprises: searching language materials related to the target label in the corpus, and searching language materials with the same meaning as the input information in the language materials related to the target label as language materials matched with the input information; or,
and searching candidate language materials with the same meaning as the input information in the corpus, comparing the labels associated with the candidate language materials with the target labels, and taking the candidate language materials associated with the labels which are successfully compared as the language materials matched with the input information.
3. The method according to any of claims 1-2, wherein the obtaining of the target conversion type of the input information is preceded by:
and accessing a preset storage area, downloading the corpus in the preset storage area and storing the corpus to the local, wherein the preset storage area is a cloud storage area or a storage area of a server side.
4. The method of claim 3, further comprising:
accessing the preset storage area at preset time intervals;
determining that a new version of a corpus is stored in the preset storage area;
and deleting the currently locally stored corpus, and downloading the new version corpus to be stored locally.
5. An information conversion method applied to a server, where the server performs data interaction with a first terminal, and the first terminal is configured to implement the information conversion method according to one of claims 1 to 4, and the method includes:
acquiring user data and public data;
training the user data and the public data to obtain a corpus so that the first terminal can download the corpus, and determining conversion information of user input information according to the corpus.
6. The method of claim 5, wherein training the user data and public data to obtain a corpus comprises:
preprocessing the user data and the public data, wherein the preprocessing comprises at least one of character proofreading, text classification, syntactic analysis, automatic word segmentation and part of speech tagging;
and training the preprocessed data to obtain a corpus.
7. The method of claim 5, further comprising:
storing the corpus into a preset storage area for a terminal to download the corpus in the preset storage area;
and updating the corpus every preset time, and storing the updated corpus of the new version into the preset storage area.
8. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing when executing the computer program to implement the method according to any of claims 1-7.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910351573.1A CN110083687B (en) | 2019-04-28 | 2019-04-28 | Information conversion method, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910351573.1A CN110083687B (en) | 2019-04-28 | 2019-04-28 | Information conversion method, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110083687A CN110083687A (en) | 2019-08-02 |
| CN110083687B true CN110083687B (en) | 2022-01-04 |
Family
ID=67417506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910351573.1A Active CN110083687B (en) | 2019-04-28 | 2019-04-28 | Information conversion method, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110083687B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112416143B (en) * | 2020-11-24 | 2022-12-27 | 维沃移动通信有限公司 | Text information editing method and device and electronic equipment |
| CN113079086B (en) * | 2021-04-07 | 2023-06-27 | 维沃移动通信有限公司 | Message transmission method, message transmission device, electronic device, and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101325746A (en) * | 2008-03-20 | 2008-12-17 | 华为技术有限公司 | Method and system for transmitting message |
| CN102523175A (en) * | 2011-12-18 | 2012-06-27 | 上海量明科技发展有限公司 | Method and system for storing icon files by transmitting data via instant communication |
| CN104125548A (en) * | 2013-04-27 | 2014-10-29 | 中国移动通信集团公司 | Method of translating conversation language, device and system |
| CN105824799A (en) * | 2016-03-14 | 2016-08-03 | 厦门幻世网络科技有限公司 | Information processing method, equipment and terminal equipment |
| CN106547925A (en) * | 2016-12-13 | 2017-03-29 | 竹间智能科技（上海）有限公司 | Adjustment conversational system responds the method and device of personality |
| CN106959987A (en) * | 2016-01-08 | 2017-07-18 | 深圳市星电商科技有限公司 | Obtain the method and system of user profile |
| CN107168676A (en) * | 2017-03-29 | 2017-09-15 | 联想(北京)有限公司 | A kind of information output method and its device |
| CN107169113A (en) * | 2017-05-19 | 2017-09-15 | 网易（杭州）网络有限公司 | Method and apparatus for realizing artificial intelligence dialogue based on user's personality |
| JP2017194983A (en) * | 2017-06-06 | 2017-10-26 | 株式会社うるる | Data conversion device, method, and computer program |
| JP2018101224A (en) * | 2016-12-19 | 2018-06-28 | エヌ・ティ・ティ・コミュニケーションズ株式会社 | Searching apparatus, searching method, and program |
| CN109002498A (en) * | 2018-06-29 | 2018-12-14 | 北京百度网讯科技有限公司 | Interactive method, device, equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202060A (en) * | 2016-06-24 | 2016-12-07 | 深圳信息职业技术学院 | A kind of character input method and device |
| CN107491442A (en) * | 2017-08-08 | 2017-12-19 | 山东中创软件工程股份有限公司 | The conversion method and device of a kind of language |
| CN108712456A (en) * | 2018-03-27 | 2018-10-26 | 上海淘票儿信息科技有限公司 | Network interaction method, equipment and system |
| CN109635251A (en) * | 2018-10-16 | 2019-04-16 | 平安普惠企业管理有限公司 | Text conversion method, device, equipment and the storage medium of application |
-
2019
- 2019-04-28 CN CN201910351573.1A patent/CN110083687B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101325746A (en) * | 2008-03-20 | 2008-12-17 | 华为技术有限公司 | Method and system for transmitting message |
| CN102523175A (en) * | 2011-12-18 | 2012-06-27 | 上海量明科技发展有限公司 | Method and system for storing icon files by transmitting data via instant communication |
| CN104125548A (en) * | 2013-04-27 | 2014-10-29 | 中国移动通信集团公司 | Method of translating conversation language, device and system |
| CN106959987A (en) * | 2016-01-08 | 2017-07-18 | 深圳市星电商科技有限公司 | Obtain the method and system of user profile |
| CN105824799A (en) * | 2016-03-14 | 2016-08-03 | 厦门幻世网络科技有限公司 | Information processing method, equipment and terminal equipment |
| CN106547925A (en) * | 2016-12-13 | 2017-03-29 | 竹间智能科技（上海）有限公司 | Adjustment conversational system responds the method and device of personality |
| JP2018101224A (en) * | 2016-12-19 | 2018-06-28 | エヌ・ティ・ティ・コミュニケーションズ株式会社 | Searching apparatus, searching method, and program |
| CN107168676A (en) * | 2017-03-29 | 2017-09-15 | 联想(北京)有限公司 | A kind of information output method and its device |
| CN107169113A (en) * | 2017-05-19 | 2017-09-15 | 网易（杭州）网络有限公司 | Method and apparatus for realizing artificial intelligence dialogue based on user's personality |
| JP2017194983A (en) * | 2017-06-06 | 2017-10-26 | 株式会社うるる | Data conversion device, method, and computer program |
| CN109002498A (en) * | 2018-06-29 | 2018-12-14 | 北京百度网讯科技有限公司 | Interactive method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110083687A (en) | 2019-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9195654B2 (en) | Automatic invocation of a dialog user interface for translation applications | |
| CN111753551B (en) | Information generation method and device based on word vector generation model | |
| CN110187780B (en) | Long text prediction method, long text prediction device, long text prediction equipment and storage medium | |
| CN112733042B (en) | Recommendation information generation method, related device and computer program product | |
| US9202142B1 (en) | Automatic assessment of books to determine suitability for audio book conversion | |
| WO2017076038A1 (en) | Method and apparatus for search and recommendation | |
| CN108280200B (en) | Method and device for pushing information | |
| US20190079644A1 (en) | Method for providing translation with emoticon, user terminal, server and computer program | |
| CN112925898B (en) | Question-answering method and device based on artificial intelligence, server and storage medium | |
| CN111291158B (en) | Information query method and device, electronic equipment and storage medium | |
| CN111178056A (en) | Deep learning based file generation method and device and electronic equipment | |
| JP2019194884A (en) | Cognitive robotics analyzer | |
| CN110162675B (en) | Method and device for generating answer sentence, computer readable medium and electronic device | |
| CN110083687B (en) | Information conversion method, equipment and storage medium | |
| CN110633017A (en) | Input method, input device and input device | |
| CN112532507A (en) | Method and device for presenting expression image and method and device for sending expression image | |
| CN113806631A (en) | Recommendation method, training method, device, equipment and news recommendation system | |
| CN117708428A (en) | Recommendation information prediction method and device and electronic equipment | |
| US11501081B1 (en) | Methods, mediums, and systems for providing a model for an end-user device | |
| CN112446214A (en) | Method, device and equipment for generating advertisement keywords and storage medium | |
| CN112087473A (en) | Document downloading method and device, computer readable storage medium and computer equipment | |
| CN107844552A (en) | Method and device for providing contents of sketch frame knowledge base | |
| CN114492306A (en) | Corpus labeling method and device, electronic equipment and storage medium | |
| CN111339291B (en) | Information display method and device and storage medium | |
| US10628860B2 (en) | System and method for creation of visual job advertisements |
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 |