CN112417210A - Body-building video query method, device, terminal and storage medium - Google Patents
Body-building video query method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN112417210A CN112417210A CN202011184818.5A CN202011184818A CN112417210A CN 112417210 A CN112417210 A CN 112417210A CN 202011184818 A CN202011184818 A CN 202011184818A CN 112417210 A CN112417210 A CN 112417210A
- Authority
- CN
- China
- Prior art keywords
- video
- fitness video
- fitness
- query
- keywords
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7844—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using original textual content or text extracted from visual content or transcript of audio data
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Abstract
The application discloses a method, a device, a terminal and a storage medium for querying a fitness video, wherein the method for querying the fitness video comprises the following steps: acquiring language keywords and health information keywords of the query fitness video; determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension; searching the target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen. The technical problem that a large amount of time is consumed in the searching and searching process of the existing fitness video is solved, the body of the user is identified through a quick searching algorithm and intelligence, the appropriate fitness video can be recommended to the user quickly, and the searching and inquiring time is saved.
Description
Technical Field
The application relates to the technical field of safety, in particular to a method, a device, a terminal and a storage medium for querying a fitness video.
Background
With the development of various network video platforms and the improvement of the fitness consciousness of the whole population, various fitness APPs are developed endlessly, the number of fitness videos on various video websites is increased, users often need to search and search when watching the fitness videos, and find favorite videos among massive videos, so that time is wasted, and the process is very decocted for users with the difficulty in selecting. Therefore, the existing fitness videos take a lot of time in the process of searching and finding.
Disclosure of Invention
The embodiment of the application aims to solve the problem that a large amount of time is consumed in the searching and searching process of the existing fitness video by providing the query method, the query device, the terminal and the storage medium of the fitness video.
In order to achieve the above object, an aspect of the present application provides a method for querying a fitness video, where the method for querying the fitness video includes the following steps:
acquiring language keywords and health information keywords of the query fitness video;
determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension;
searching a target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen.
Optionally, the step of determining search dimensions for querying the fitness video according to the language keywords and the health information keywords, where each search dimension sets a corresponding search function includes:
classifying the language keywords and the health information keywords according to query intentions to determine search dimensions for querying the fitness video;
and the registration query module is used for setting a corresponding search function for each search dimension according to the query module.
Optionally, the step of searching for the target fitness video according to the search function includes:
sequentially executing the search function to generate a query statement of the fitness video;
searching the target fitness video matched with the query sentence in a video database of the terminal.
Optionally, the step of obtaining the language keyword and the health information keyword for querying the fitness video includes:
receiving a voice instruction sent by a user, and acquiring the language keywords according to the voice instruction;
and acquiring images of all parts of the body of the user, and determining the health information keywords according to the images of all parts.
Optionally, after the step of obtaining images of parts of the body of the user and determining the health information keyword according to the images of the parts, the method further includes:
respectively setting weighted values for the images of all the parts, and sending the images of all the parts to a cloud end to obtain muscle content corresponding to all the parts;
and acquiring the ratio of the weight value to the muscle content, and determining the health information keywords to be inquired according to the ratio.
Optionally, the receiving a voice instruction sent by a user, and the step of obtaining the language keyword according to the voice instruction includes:
acquiring a voice recognition text corresponding to the voice instruction;
and extracting the language key words in the voice recognition text according to a key word segmentation module.
Optionally, after the step of searching the video database of the terminal for the target fitness video matching the query statement, the method further includes:
if a plurality of target fitness videos matched with the query statement are searched, obtaining playing information corresponding to each target fitness video;
and determining the target body-building video to be played according to the playing information.
In addition, to achieve the above object, another aspect of the present application further provides a query device for a fitness video, the device comprising:
the acquisition module is used for acquiring the language keywords and the health information keywords of the query fitness video;
the determining module is used for determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and each search dimension is provided with a corresponding search function;
and the display module is used for searching the target fitness video according to the search function and displaying the searched target fitness video on a terminal screen.
In addition, in order to achieve the above object, in another aspect of the present application, a terminal is further provided, where the terminal includes a memory, a processor, and a query program of a fitness video stored in the memory and running on the processor, and the processor implements the steps of the query method of the fitness video when executing the recharge program.
In addition, to achieve the above object, another aspect of the present application further provides a computer readable storage medium, on which a query program of a fitness video is stored, and when the query program of the fitness video is executed by a processor, the steps of the query method of the fitness video are implemented.
In the embodiment, the language keywords and the health information keywords of the query fitness video are obtained; determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension; searching the target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen. By means of a quick search algorithm and intelligent identification of the user stature, the problem that a large amount of time is consumed in the searching and searching process of the existing fitness video is solved, the appropriate fitness video can be recommended to the user quickly, and the searching and inquiring time is saved.
Drawings
Fig. 1 is a schematic terminal structure diagram of a hardware operating environment according to an embodiment of the present application;
FIG. 2 is a schematic flowchart of a first embodiment of a query method for a fitness video according to the present application;
FIG. 3 is a flowchart illustrating a second embodiment of the query method for fitness video according to the present application;
FIG. 4 is a flowchart illustrating a third embodiment of the query method of the fitness video according to the present application;
fig. 5 is a schematic flow chart illustrating a process of acquiring a language keyword and a health information keyword of a query fitness video according to the query method of the fitness video;
fig. 6 is a schematic flow chart illustrating a process of receiving a voice command sent by a user and acquiring the language keyword according to the voice command in the query method for the fitness video according to the present application;
fig. 7 is a schematic flow chart illustrating a step of acquiring images of various parts of a user's body and determining the health information keyword according to the images of the various parts in the method for querying a fitness video according to the present application;
fig. 8 is a schematic flowchart illustrating a process of determining search dimensions for querying a fitness video according to the language keywords and the health information keywords in the method for querying a fitness video according to the present application, where each search dimension is configured with a corresponding search function;
fig. 9 is a block diagram of the query device of the exercise video of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The main solution of the embodiment of the application is as follows: acquiring language keywords and health information keywords of the query fitness video; determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension; searching the target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen.
Due to the development of various network video platforms and the improvement of the fitness consciousness of the whole population, various fitness APPs are developed endlessly, more and more fitness videos are provided on various large video websites, and users often need to search and find the fitness videos when watching the fitness videos, so that the users find favorite videos in the massive videos, and time is wasted. The method comprises the steps of obtaining a language keyword and a health information keyword of a query fitness video; determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension; searching the target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen. By means of a quick search algorithm and intelligent identification of the user stature, the problem that a large amount of time is consumed in the searching and searching process of the existing fitness video is solved, the appropriate fitness video can be recommended to the user quickly, and the searching and inquiring time is saved.
As shown in fig. 1, fig. 1 is a schematic terminal structure diagram of a hardware operating environment according to an embodiment of the present application.
As shown in fig. 1, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the terminal may further include a camera, a Radio Frequency (RF) circuit, a sensor, a remote controller, an audio circuit, a WiFi module, a detector, and the like. Of course, the terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer and a temperature sensor, which are not described herein again.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 does not constitute a limitation of the terminal device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer-readable storage medium, may include therein an operating system, a network communication module, a user interface module, and a query program of a fitness video.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 1001 may be configured to invoke the query program of the fitness video stored in the memory 1005 and perform the following operations:
acquiring language keywords and health information keywords of the query fitness video;
determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension;
searching a target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen.
Referring to fig. 2, fig. 2 is a schematic flowchart of a first embodiment of the query method of the fitness video of the present application.
While embodiments of the present application provide embodiments of a query method for a workout video, it should be noted that although a logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different from that shown or described herein.
The query method of the fitness video comprises the following steps:
step S10, acquiring language keywords and health information keywords of the query fitness video;
when the terminal receives a query instruction sent by a user, the query instruction can be a voice instruction or input text information, and language keywords and health information keywords of the query fitness video are further obtained based on the query instruction, wherein the language keywords comprise a fitness video name, a coach name, a video type, video duration and the like; the health information keywords include other body parts such as the shoulder, neck, waist and abdomen, arms and legs of the user.
Further, referring to fig. 5, the step of obtaining the language keyword and the health information keyword for querying the fitness video includes:
step S11, receiving a voice instruction sent by a user, and acquiring the language keyword according to the voice instruction;
when detecting that a user triggers a 'fitness video quick recommendation' module, the terminal starts a natural language keyword acquisition module, wherein the natural language keyword acquisition module is mainly used for acquiring language keywords in a voice recognition text. Meanwhile, reminding a user in a pop-up window form or a voice form on a terminal screen to 'please speak your needs', inputting voice into the control equipment after the user receives the reminding information of the terminal, so that the control equipment can receive voice inquiry information of a video, and then sending the voice inquiry information to the terminal by the control equipment; or, the user directly inputs voice into the terminal, and the terminal directly acquires the voice query information input by the user; the terminal performs voice recognition on the received voice query information, converts the voice query information into a text to acquire a query sentence of the video, and acquires a language keyword based on the query sentence. For example: the method comprises the steps that a terminal receives voice query information ' i want to see the body building video of the pamela ', the terminal converts the voice query information into text format ' i want to see the body building video of the pamela ', a video query sentence ' i want to see the body building video of the pamela ' is obtained, and language keywords of the query sentence are ' the pamela ' and the body building video ' further; the language keyword is extracted by a keyword segmentation module in the terminal, and therefore, referring to fig. 6, the step of receiving a voice instruction sent by a user and obtaining the language keyword according to the voice instruction includes:
step S110, acquiring a voice recognition text corresponding to the voice command;
and step S111, extracting language keywords in the voice recognition text according to a keyword segmentation module.
When the terminal receives a body-building video query instruction sent by a user based on voice, voice recognition text information in audio is extracted by using a voice recognition tool, and the voice recognition tool can be an existing voice recognition engine. The active speech of the speech recognition tool can be selected according to actual requirements, and can be Chinese, English or other different languages. And further preprocessing the voice recognition text information through a keyword segmentation module, wherein the preprocessing of the voice recognition text information comprises the following steps: word segmentation, word stop removal and word vectorization of the text. The word segmentation of the text plays an important role in extracting the text features, such as an example sentence' i want to see the fitness video of pamela! "the word segmentation result is: i, want, see, Pamerala, fitness video! . The structures of the main and the predicate objects and the noun verbs in the sentences are extracted respectively. Stop words refer to words in the text message that do not contribute to the analysis of the text, such as "of", "of! "etc., the purpose of removing stop words is to improve speech recognition text analysis accuracy. Word vectorization refers to the expression of a word in a vector form, which has the function of converting input text information into a numerical form, and has various algorithms, mainly including bag-of-words, CBOW, and Skip-gram algorithms.
The keyword segmentation module analyzes the extracted segmentation words to determine whether the speech recognition text contains keywords. Specifically, it is required to determine whether the speech recognition text contains at least one keyword, for example, "pamela, fitness video" is included in the speech recognition text determined by the terminal, so that "pamela" and "fitness video" can be determined as the language keyword. For another example, if the voice recognition text determined by the terminal is "i want to sing", it may be determined that the voice recognition text does not include the language keyword, and at this time, the terminal displays a fitness video that is not found and is matched with the voice recognition text on the display interface, so as to remind the user to input the fitness video query instruction again.
Optionally, the user may directly input text information for querying the fitness video in a search bar of the fitness video search page, and the text information is identified and analyzed by the keyword segmentation extraction module, so as to determine the language keywords of the video query.
In step S12, images of the respective parts of the user' S body are acquired, and the health information keyword is specified from the images of the respective parts.
The terminal shoots images of all parts of the body of the user, such as other body parts of the shoulder, neck, waist, abdomen, arms, legs and the like based on the camera, and analyzes the shot images of all parts to determine a health information keyword, wherein the health information keyword is a name corresponding to each department. Therefore, referring to fig. 7, after the step of obtaining images of each part of the user's body and determining the health information keyword according to the images of each part, the method further includes:
step S120, respectively setting weight values for the images of all the parts, and sending the images of all the parts to a cloud end to obtain muscle content corresponding to all the parts;
and S121, obtaining a ratio of the weight value to the muscle content, and determining a health information keyword to be inquired according to the ratio.
The terminal acquires images of all parts shot by the camera, and sets corresponding weight values for all parts based on the images of all parts, wherein the weight values set for the shoulder, neck, waist, abdomen, arms and legs are respectively 20%, 30%, 22% and 28%. And further sending the images of all parts to a cloud end, and the cloud end obtains the muscle content corresponding to each part based on the analysis of the images and sends the muscle content to the terminal. The terminal executes division operation on the muscle content and the weighted value corresponding to each part, such as muscle content/weighted value, so as to obtain the ratio of the muscle content and the weighted value, and the health information keyword to be inquired is determined according to the ratio. Specifically, the names of the parts with the division result smaller than 1 are counted, and the names of the parts with the division result smaller than 1 are used as the health information keywords to be queried. For example: the arm muscle content is 10%, and the arm weight is 20%, the arm muscle content/arm result is less than 1, which indicates that the arm muscle content is high, and the body shape is greatly influenced, so that the part is the key part for body building. For another example: the waist and abdomen muscle content is 30 percent, the weight of the waist and abdomen is 30 percent, the result of the waist and abdomen muscle content/waist and abdomen is equal to 1, which indicates that the waist and abdomen muscle content is lower and the body is greatly influenced, therefore, the part is not the key part for body building.
Step S20, determining search dimensions of the query fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension;
when the terminal obtains the language keywords and the health information keywords of the body-building video query, the control system starts a QueryHandle fast search module and a dimension analysis module, and search dimensions are formed based on the dimension analysis module, such as: "pamela" is the "name of the person" dimension, the fitness video is the "channel" dimension, and the waist and abdomen is the "video name" dimension. And setting a corresponding search function for each search dimension, wherein the search function corresponding to the Person is PersonQueryHandle.
Further, referring to fig. 8, the step of determining search dimensions for querying the fitness video according to the language keywords and the health information keywords, where each search dimension sets a corresponding search function includes:
step S21, classifying the language keywords and the health information keywords according to the query intention to determine the search dimension of the query fitness video;
step S22, registering a query module, and setting a corresponding search function for each search dimension according to the query module.
The terminal classifies the language keywords and the health information keywords according to the Query intention to determine the search dimension of the Query fitness video, and specifically, the Query intention is identified based on Query understanding, wherein the Query understanding is a process of analyzing the user search string and understanding the user intention and is a task of standard natural language processing. Where Query is understood to be as shown in table 1 below:
TABLE 1
| Query | I want to see the fitness video of Pamerala! |
| Query rewrite | Playing fitness video of Pamerala and fitness video of Pamerala |
| Query intent | Video playback |
| NER | Pamela (name of person); body-building video (video type) |
Only some operations understood by Query are listed in table 1, and other operations such as Query error correction, word segmentation, word weight, synonyms, and the like are also included. As understood from Query in table 1, if the language keyword and the health information keyword obtained by the terminal include "pamela", "fitness video", and "arm", it may be determined that the object of the search intention is "video", and the search intention of the object is "video name", "video content", "video character", and "play duration", and the like. For each search intention, a different search dimension is set, for example: the fitness video is the "channel" dimension, and the "arm" is the "video name" dimension, etc. Further registering a QueryHandle module, namely a query module, wherein the query module is mainly used for callback; when a corresponding search function needs to be set for each search dimension, a registered query module is called, and a search function is set based on the query module, for example, the search function corresponding to Person is PersonQueryHandle; the search function corresponding to a channel is a channelQueryHandle.
And step S30, searching a target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen.
The terminal searches the body-building video by using a QueryHandle fast search algorithm, specifically, the terminal searches a target body-building video according to a search function, the target body-building video is a video which a user wants to play, and if the voice sent by the user is 'i want to see the body-building video of Pamera', the target body-building video is 'the body-building video of Pamera'. When a plurality of matching target fitness videos are searched in the video database based on the search function, the target fitness videos can be arranged and displayed on the terminal page so that the user can select a suitable video. Or obtaining the searched historical playing records of the target fitness videos, such as the playing times, the playing duration, comments and other information to determine the videos in which the user is interested, recommending the target fitness videos to the user, and displaying the videos on a terminal screen.
The embodiment extracts language keywords in the voice recognition text through a keyword segmentation module, and determines health information keywords to be queried based on the ratio of the weight value to the muscle content; determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension; and further searching the target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen. By means of a quick search algorithm and intelligent identification of the user stature, the problem that a large amount of time is consumed in the searching and searching process of the existing fitness video is solved, the appropriate fitness video can be recommended to the user quickly, and the searching and inquiring time is saved.
Further, referring to fig. 3, a second embodiment of the query method of the fitness video is provided.
The second embodiment of the query method of the fitness video differs from the first embodiment of the query method of the fitness video in that the step of searching for the target fitness video according to the search function comprises:
step S31, sequentially executing the search function to generate the query sentence of the fitness video;
and step S32, searching the target fitness video matched with the query sentence in a video database of the terminal.
The terminal sequentially executes the set search functions to generate a complete ElasticSearch query statement: search rule 1 (name pamela), rule2 (channel body building), rule3 (name of video waist), Query for elastic Search according to Query. Specifically, after the terminal acquires the query statement, each keyword in the query statement, such as pamela, channel fitness, waist and abdomen and the like, is acquired; and further acquiring one or more target fitness videos with the most matching number with the keywords in the video data.
In the embodiment, the query sentences of the body-building videos are generated by sequentially executing the search functions through the QueryHandle fast search algorithm, and the target body-building videos matched with the query sentences are searched in the video database, so that the videos desired by the user can be quickly searched, the search and query time is saved, and the search and query efficiency of the videos is improved.
Further, referring to fig. 4, a third embodiment of the query method of the fitness video of the present application is provided.
The third embodiment of the query method for the fitness video differs from the first and second embodiments of the query method for the fitness video in that, after the step of searching the video database of the terminal for the target fitness video matching the query sentence, the method further comprises:
step S320, if a plurality of target fitness videos matched with the query sentence are searched, obtaining playing information corresponding to each target fitness video;
and S321, determining the target body-building video to be played according to the playing information.
Usually, a plurality of target fitness videos matched with the query sentence are searched during video search, and at this time, the target fitness videos to be played can be determined by obtaining playing information corresponding to each target fitness video, such as popularity information of playing, number of clicks, score, collection amount, number of comments of the video, and the like. Specifically, the popularity of the video is comprehensively determined through the number of clicks, the score, the collection amount, the number of comments and the like of the video, for example, the number of comments and the number of clicks corresponding to each target fitness video are obtained, for example, the number of comments of the video a is 500, and the number of clicks is 2000; the number of comments of video B is 200, and the number of clicks is 3000, it is determined that video a is more popular than video B. And sequencing all the target fitness videos according to the popularity, wherein the videos which are sequenced in the front can be preferentially recommended to the user. Or extracting keywords from the brief introduction and/or the comment of the video to obtain at least one alternative keyword, matching the extracted keyword with keywords in a tag library, storing template keywords pre-stored by a user in the tag library, such as 'very good video', 'good effect' and the like, and preferentially recommending the video with high matching degree to the user. Specifically, when extracting keywords from the brief introduction and/or the comment of the video, the frequency N of occurrence of a certain word is defined first, that is, the keyword is extracted when a certain word appears at least N times in the brief introduction and/or the comment, and N can be set by itself. And further searching keywords with high occurrence frequency in the tag library, and if the number of the searched keywords is more, indicating that the popularity of the target fitness video is high, and preferentially recommending the video with high popularity to the user.
Optionally, when detecting that the user triggers the "fast fitness video recommendation" module, the terminal obtains pre-stored ratios of weighted values and muscle contents corresponding to each part of the body of the user when the user watches the video last time, and watching record information of the fitness video. And determining videos in which the user is interested based on the watching record information, determining videos matched with the body condition of the user in the interested videos based on the ratio of the weight value and the muscle content respectively corresponding to each part, and recommending the matched videos to the user.
In the embodiment, when a plurality of target fitness videos matched with the query statement are searched, the target fitness videos to be played are determined by acquiring the playing information corresponding to each target fitness video, so that the user can directly acquire favorite videos, and the requirements of the user are met.
In addition, referring to fig. 9, the present application further provides a query device for a fitness video, the device comprising:
the acquisition module 10 is used for acquiring the language keywords and the health information keywords of the query fitness video;
the determining module 20 is configured to determine search dimensions for querying the fitness video according to the language keywords and the health information keywords, where each search dimension sets a corresponding search function;
and the display module 30 is configured to search for a target fitness video according to the search function, and display the searched target fitness video on a terminal screen.
Further, the determining module 20 includes: a classification unit and a registration unit;
the classification unit is used for classifying the language keywords and the health information keywords according to query intentions so as to determine search dimensions of the query fitness video;
the registration unit is used for registering a query module and setting a corresponding search function for each search dimension according to the query module.
Further, the display module 30 includes an execution unit and a search unit;
the execution unit is used for sequentially executing the search function to generate a query statement of the fitness video;
the searching unit is used for searching the target fitness video matched with the query sentence in a video database of the terminal.
Further, the obtaining module 10 includes: a receiving unit and an obtaining unit;
the receiving unit is used for receiving a voice instruction sent by a user and acquiring the language keywords according to the voice instruction;
the acquiring unit is used for acquiring images of all parts of the body of the user and determining the health information keywords according to the images of all parts.
Further, the acquiring unit comprises a setting subunit and an acquiring subunit;
the setting subunit is used for respectively setting weighted values for the images of the various parts and sending the images of the various parts to a cloud so as to acquire the muscle content corresponding to the various parts;
the acquiring subunit is configured to acquire a ratio between the weight value and the muscle content, and determine a health information keyword to be queried according to the ratio.
Further, the receiving unit includes: a receiving subunit and an extracting subunit;
the receiving subunit is configured to acquire a speech recognition text corresponding to the speech instruction;
and the extraction subunit is used for extracting the language keywords in the voice recognition text according to the keyword segmentation module.
Further, the search unit comprises an acquisition subunit and a determination subunit;
the obtaining subunit is configured to obtain, if a plurality of target fitness videos matched with the query statement are searched, play information corresponding to each target fitness video;
and the character determining unit is used for determining the target body building video to be played according to the playing information.
The implementation of the functions of each module of the query device for the fitness video is similar to the process in the embodiment of the method, and thus, the detailed description is omitted.
In addition, the application also provides a terminal, the terminal comprises a memory, a processor and a query program of the fitness video, wherein the query program is stored in the memory and runs on the processor; determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension; searching the target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen. By utilizing the QueryHandle fast search algorithm and the method for intelligently identifying the stature of the user, the proper fitness video is quickly recommended to the user, the problem that a large amount of time is consumed in the searching and searching process of the conventional fitness video is solved, and the searching and inquiring time is saved.
In addition, the present application also provides a computer readable storage medium, on which a query program of the fitness video is stored, and when being executed by a processor, the query program of the fitness video implements the steps of the query method of the fitness video as described above.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
While alternative embodiments of the present application have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following appended claims be interpreted as including alternative embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. A query method of a fitness video is characterized by comprising the following steps:
acquiring language keywords and health information keywords of the query fitness video;
determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and setting a corresponding search function for each search dimension;
searching a target fitness video according to the search function, and displaying the searched target fitness video on a terminal screen.
2. The method for querying a fitness video according to claim 1, wherein the step of determining search dimensions for querying the fitness video according to the language keywords and the health information keywords, each search dimension setting a corresponding search function comprises:
classifying the language keywords and the health information keywords according to query intentions to determine search dimensions for querying the fitness video;
and the registration query module is used for setting a corresponding search function for each search dimension according to the query module.
3. The method for querying a fitness video of claim 1, wherein the step of searching for the target fitness video according to the search function comprises:
sequentially executing the search function to generate a query statement of the fitness video;
searching the target fitness video matched with the query sentence in a video database of the terminal.
4. The method for querying a fitness video according to claim 1, wherein the step of obtaining the language keyword and the health information keyword for querying the fitness video comprises:
receiving a voice instruction sent by a user, and acquiring the language keywords according to the voice instruction;
and acquiring images of all parts of the body of the user, and determining the health information keywords according to the images of all parts.
5. The method for querying a fitness video according to claim 4, after the step of acquiring images of the respective parts of the body of the user and determining the health information keyword from the images of the respective parts, further comprising:
respectively setting weighted values for the images of all the parts, and sending the images of all the parts to a cloud end to obtain muscle content corresponding to all the parts;
and acquiring the ratio of the weight value to the muscle content, and determining the health information keywords to be inquired according to the ratio.
6. The method for querying a fitness video according to claim 4, wherein the step of receiving a voice command sent by a user and obtaining the language keyword according to the voice command comprises:
acquiring a voice recognition text corresponding to the voice instruction;
and extracting the language key words in the voice recognition text according to a key word segmentation module.
7. The method for querying a fitness video according to claim 3, wherein after the step of searching the video database of the terminal for the target fitness video matching the query sentence, the method further comprises:
if a plurality of target fitness videos matched with the query statement are searched, obtaining playing information corresponding to each target fitness video;
and determining the target body-building video to be played according to the playing information.
8. An inquiry apparatus for a fitness video, the apparatus comprising:
the acquisition module is used for acquiring the language keywords and the health information keywords of the query fitness video;
the determining module is used for determining search dimensions for inquiring the fitness video according to the language keywords and the health information keywords, and each search dimension is provided with a corresponding search function;
and the display module is used for searching the target fitness video according to the search function and displaying the searched target fitness video on a terminal screen.
9. A terminal, characterized in that the terminal comprises a memory, a processor and a query program of a fitness video stored on the memory and running on the processor, and the processor implements the steps of the method according to any one of claims 1 to 7 when executing the query program of the fitness video.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a query program of a fitness video, which when executed by a processor implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011184818.5A CN112417210A (en) | 2020-10-29 | 2020-10-29 | Body-building video query method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011184818.5A CN112417210A (en) | 2020-10-29 | 2020-10-29 | Body-building video query method, device, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417210A true CN112417210A (en) | 2021-02-26 |
Family
ID=74826868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011184818.5A Pending CN112417210A (en) | 2020-10-29 | 2020-10-29 | Body-building video query method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417210A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065020A (en) * | 2021-03-23 | 2021-07-02 | 上海兽鸟智能科技有限公司 | Intelligent fitness equipment, use method and terminal |
| WO2023000779A1 (en) * | 2021-07-23 | 2023-01-26 | 北京字节跳动网络技术有限公司 | Information query method and related device thereof |
-
2020
- 2020-10-29 CN CN202011184818.5A patent/CN112417210A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065020A (en) * | 2021-03-23 | 2021-07-02 | 上海兽鸟智能科技有限公司 | Intelligent fitness equipment, use method and terminal |
| WO2023000779A1 (en) * | 2021-07-23 | 2023-01-26 | 北京字节跳动网络技术有限公司 | Information query method and related device thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108829822B (en) | Media content recommendation method and device, storage medium and electronic device | |
| CN108287858B (en) | Semantic extraction method and device for natural language | |
| CN106649786B (en) | Answer retrieval method and device based on deep question answering | |
| CN105824959B (en) | Public opinion monitoring method and system | |
| CN106156204B (en) | Text label extraction method and device | |
| CN110263248B (en) | Information pushing method, device, storage medium and server | |
| US20180336193A1 (en) | Artificial Intelligence Based Method and Apparatus for Generating Article | |
| CN108108426B (en) | Understanding method and device for natural language question and electronic equipment | |
| CN102119385B (en) | Method and subsystem for searching media content within a content-search-service system | |
| CN108920450B (en) | Knowledge point reviewing method based on electronic equipment and electronic equipment | |
| CN109558513B (en) | Content recommendation method, device, terminal and storage medium | |
| CN110413875A (en) | A kind of method and relevant apparatus of text information push | |
| CN109408821B (en) | Corpus generation method and device, computing equipment and storage medium | |
| CN104915420B (en) | Knowledge base data processing method and system | |
| CN113094552A (en) | Video template searching method and device, server and readable storage medium | |
| CN109522397B (en) | Information processing method and device | |
| CN113704507B (en) | Data processing method, computer device and readable storage medium | |
| CN112417210A (en) | Body-building video query method, device, terminal and storage medium | |
| CN111260428A (en) | Commodity recommendation method and device | |
| CN110717038B (en) | Object classification method and device | |
| CN108280081B (en) | Method and device for generating webpage | |
| CN106484913B (en) | Target picture determining method and server | |
| CN109753646B (en) | Article attribute identification method and electronic equipment | |
| CN112581297B (en) | Information pushing method and device based on artificial intelligence and computer equipment | |
| CN112487159B (en) | Search method, search device, and computer-readable 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 |