CN117648407A - Sports event data statistics method and system - Google Patents
Sports event data statistics method and system Download PDFInfo
- Publication number
- CN117648407A CN117648407A CN202410107396.3A CN202410107396A CN117648407A CN 117648407 A CN117648407 A CN 117648407A CN 202410107396 A CN202410107396 A CN 202410107396A CN 117648407 A CN117648407 A CN 117648407A
- Authority
- CN
- China
- Prior art keywords
- event data
- sentences
- statistical
- acquiring
- pending
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012216 screening Methods 0.000 claims abstract description 17
- 230000014509 gene expression Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 10
- 230000000386 athletic effect Effects 0.000 claims description 7
- 238000013136 deep learning model Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process 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
- 230000001737 promoting effect Effects 0.000 description 1
Abstract
The invention relates to the technical field of data statistics, and particularly discloses a method and a system for counting sports event data, wherein the method comprises the following steps: s1: determining statistics personnel of the current event purpose; s2: acquiring input voice in a collection period in real time; s3: converting input voice into a text format, and acquiring all sentences in the text; screening undetermined sentences and determining undetermined positions; acquiring a text after the position is to be determined, and generating a statistical format according to the text after the position is to be determined; acquiring the statistical format of all pending sentences; s4: and generating a statistical table and sending the statistical table to a statistics person. The invention can reduce the condition of voice input errors caused by excessive surrounding noise in the process of counting the sports event data through voice, and improve the efficiency of counting the sports event data.
Description
Technical Field
The invention relates to the technical field of data statistics, in particular to a method and a system for counting sports event data.
Background
Sports (physical education, abbreviated as PE or P.E.) is a complex social culture phenomenon, which is a conscious, purposeful and organized social activity taking physical and intellectual activities as basic means and achieving the purposes of promoting overall development, improving physical quality and overall education level, enhancing physical fitness and exercise ability, improving life style and improving life quality according to the rules of growth and development, skill formation, functional improvement and the like of human bodies.
A sporting event refers to a regular game of a relatively scaled rank. Taking basketball game as an example, the types of data to be counted are more, such as scoring, assisting, basketball, etc., but the situation on the competition field is unpredictable, which may result in larger data quantity to be counted, but the existing sports event data statistics usually adopts a manual recording mode, the manpower resource cost is high, and the data statistics mode is single.
In a chinese patent with patent publication No. CN109360589a, a method and system for counting sports event data are disclosed, and the scheme mainly includes data input, data classification and storage, and data retrieval and output. In the data input process, an audio input module is included. In practical situations, the sports event field is often intensive in personnel, so a lot of noise is generated, and the audio input module cannot distinguish the noise, which may be interfered by the outside when the audio input module is used for sports event data statistics, resulting in data input errors. In addition, the audio input module comprises a mispronounced identification unit and a mispronounced prompting unit, which may cause the mispronounced prompting unit to always prompt the condition of input errors, thereby affecting the efficiency of data statistics.
Disclosure of Invention
The invention aims to provide a method and a system for counting sports event data, which solve the technical problems.
The aim of the invention can be achieved by the following technical scheme:
a method of sports event data statistics, comprising the steps of:
s1: determining statistics personnel of the current event, wherein the statistics personnel are staff responsible for counting sports event data, and the sports event data comprises athlete names, scores, attack aiding times, foul times and error times;
s2: setting an acquisition period, and acquiring input voice in real time in the acquisition period, wherein the input voice is a voice signal sent by the statistics personnel, and the process of acquiring the input voice specifically comprises the following steps:
establishing a database, wherein voiceprints of statistical staff are stored in the database, establishing a voiceprint recognition model through a deep learning model, and training and verifying the voiceprint recognition model by using the database;
acquiring the voice signal in the acquisition period in real time, inputting the voice signal into a voiceprint recognition model, and acquiring input voice;
s3: converting the input voice into a text format, acquiring all sentences in the text, and executing a scoring step:
s31: screening sentences containing the names of the athletes through regular expressions, defining the sentences as pending sentences, marking the position of the last character in the names of the athletes in the pending sentences, and defining the positions as pending positions;
s32: in the pending sentences, acquiring texts after the pending positions, searching whether the texts comprise sports event data or not through a regular expression, and generating statistical formats of the current pending sentences, wherein the statistical formats are player name-sports event data corresponding to the current pending sentences;
s33: repeating the steps S31-S32 to obtain the statistical format of all pending sentences;
s4: generating a statistical table, wherein the statistical table comprises the score sum, the attack total times, the foul total times and the error total times of each athlete, and sending the statistical table to a statistical staff after the acquisition period is finished.
As a further scheme of the invention: in the step S31, the following steps are performed:
step one: acquiring the name of the athlete of the current event project, and acquiring the tone score m of each Chinese character in the name;
step two: calculating score sum of athletesWherein m is i Tone assignment for representing the i-th kanji in the athlete's name;
step three: ranking the athletes according to the scoring sums, wherein the ranking is more rearward as the scoring sums are larger;
step four: starting from the first digit in the sequence, screening out pending sentences containing names of corresponding athletes through a regular expression;
step five: and repeating the first step to the fourth step, and screening out all pending sentences.
As a further scheme of the invention: in the first step, the specific assigning process comprises the following steps: the level of yin, level of yang, up-sounding and down-sounding are respectively assigned to 1, 2, 3 and 4.
As a further scheme of the invention: in the third step, when two or more scoring sums are the same, the scoring sums are sorted according to the first pinyin of the name of the athlete.
As a further scheme of the invention: in the step S31, when there are two or more names of athletes in a sentence, the following steps are performed:
searching whether the sentence comprises the body event data or not through a regular expression;
when the sentence does not include the body event data, no subsequent processing is performed;
when the sentence includes the body event data, prompting a statistics person to re-input the sentence and prompting the statistics person to adjust the voice input format to be the statistical format when the input voice is not recognized.
As a further scheme of the invention: in the step S32, when the athletic event data is not included in a certain pending sentence, the pending sentence does not perform the subsequent steps.
As a further scheme of the invention: in the step S32, when two or more sports event data are included in a predetermined sentence, the following steps are executed:
and obtaining the quantity a of the sports event data in the sentence, and generating a statistical formats of the sentence according to the sports event data in the sentence.
A athletic event data statistics system, comprising:
an initial module: determining statistics personnel of the current event, wherein the statistics personnel are staff responsible for counting sports event data, and the sports event data comprises athlete names, scores, attack aiding times, foul times and error times;
an input determination module: setting an acquisition period, and acquiring input voice in real time in the acquisition period, wherein the input voice is a voice signal sent by the statistics personnel, and the process of acquiring the input voice specifically comprises the following steps:
establishing a database, wherein voiceprints of statistical staff are stored in the database, establishing a voiceprint recognition model through a deep learning model, and training and verifying the voiceprint recognition model by using the database;
acquiring the voice signal in the acquisition period in real time, inputting the voice signal into a voiceprint recognition model, and acquiring input voice;
and a recording module: converting the input voice into a text format, acquiring all sentences in the text, and executing a scoring step:
s31: screening sentences containing the names of the athletes through regular expressions, defining the sentences as pending sentences, marking the position of the last character in the names of the athletes in the pending sentences, and defining the positions as pending positions;
s32: in the pending sentences, acquiring texts after the pending positions, searching whether the texts comprise sports event data or not through a regular expression, and generating statistical formats of the current pending sentences, wherein the statistical formats are player name-sports event data corresponding to the current pending sentences;
s33: repeating the steps S31-S32 to obtain the statistical format of all pending sentences;
and a sending module: generating a statistical table, wherein the statistical table comprises the score sum, the attack total times, the foul total times and the error total times of each athlete, and sending the statistical table to a statistical staff after the acquisition period is finished.
The invention has the beneficial effects that: the invention is suitable for basketball game, in the invention, firstly, the type of sports event data to be counted is determined, which is the basis of subsequent processing; and then, acquiring the voice signal acquired in the acquisition period, and recognizing the input voice from the voice signal, wherein the acquisition period is from the starting time to the ending time of the basketball game, and the input voice is recognized through voiceprints, and the voiceprints have the characteristics of specificity and relative stability. Experiments prove that whether a speaker deliberately imitates the voice and the mood of other people or whistle lightly speaks, the voiceprint of the speaker is unchanged all the time even if the speaker imitates the wonderful Chinese word; secondly, screening undetermined sentences through regular expressions, wherein the undetermined sentences are used for reducing subsequent processing capacity; because it can be understood that the statistics personnel can also carry out the irrelevant exchange of the statistics of the sports event data, such as daily exchange, etc. in the working process; therefore, the invention performs preliminary screening through the regular expression, reduces the subsequent data processing amount and saves the computing resource; searching whether the sentence comprises sports event data or not through a regular expression, and generating a statistical format; because it will be appreciated that in practice, the statistics may be drunk by the player for his wonderful performance, or as "a's pass is good", where the player's name is mentioned, but the sports event data may not be counted; finally, a statistical table is generated and sent to a statistics staff, and the collected data is visually displayed. The invention can reduce the condition of voice input errors caused by excessive surrounding noise in the process of counting the sports event data through voice, and improve the efficiency of counting the sports event data.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method for counting sports event data according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention is a method for counting sports event data, comprising the following steps:
s1: determining statistics personnel of the current event, wherein the statistics personnel are staff responsible for counting sports event data, and the sports event data comprises athlete names, scores, attack aiding times, foul times and error times;
s2: setting an acquisition period, and acquiring input voice in real time in the acquisition period, wherein the input voice is a voice signal sent by the statistics personnel, and the process of acquiring the input voice specifically comprises the following steps:
establishing a database, wherein voiceprints of statistical staff are stored in the database, establishing a voiceprint recognition model through a deep learning model, and training and verifying the voiceprint recognition model by using the database;
acquiring the voice signal in the acquisition period in real time, inputting the voice signal into a voiceprint recognition model, and acquiring input voice;
s3: converting the input voice into a text format, acquiring all sentences in the text, and executing a scoring step:
s31: screening sentences containing the names of the athletes through regular expressions, defining the sentences as pending sentences, marking the position of the last character in the names of the athletes in the pending sentences, and defining the positions as pending positions;
s32: in the pending sentences, acquiring texts after the pending positions, searching whether the texts comprise sports event data or not through a regular expression, and generating statistical formats of the current pending sentences, wherein the statistical formats are player name-sports event data corresponding to the current pending sentences;
s33: repeating the steps S31-S32 to obtain the statistical format of all pending sentences;
s4: generating a statistical table, wherein the statistical table comprises the score sum, the attack total times, the foul total times and the error total times of each athlete, and sending the statistical table to a statistical staff after the acquisition period is finished.
It should be noted that, the present invention is applicable to basketball game, in the present invention, firstly, the kind of sports event data to be counted is determined, which is the basis of the subsequent processing; and then, acquiring the voice signal acquired in the acquisition period, and recognizing the input voice from the voice signal, wherein the acquisition period is from the starting time to the ending time of the basketball game, and the input voice is recognized through voiceprints, and the voiceprints have the characteristics of specificity and relative stability. Experiments prove that whether a speaker deliberately imitates the voice and the mood of other people or whistle lightly speaks, the voiceprint of the speaker is unchanged all the time even if the speaker imitates the wonderful Chinese word; secondly, screening undetermined sentences through regular expressions, wherein the undetermined sentences are used for reducing subsequent processing capacity; because it can be understood that the statistics personnel can also carry out the irrelevant exchange of the statistics of the sports event data, such as daily exchange, etc. in the working process; therefore, the invention performs preliminary screening through the regular expression, reduces the subsequent data processing amount and saves the computing resource; searching whether the sentence comprises sports event data or not through a regular expression, and generating a statistical format; because it will be appreciated that in practice, the statistics may be drunk by the player for his wonderful performance, or as "a's pass is good", where the player's name is mentioned, but the sports event data may not be counted; finally, a statistical table is generated and sent to a statistics staff, and the collected data is visually displayed.
In another preferred embodiment of the present invention, in the step S31, the following steps are performed:
step one: acquiring the name of the athlete of the current event project, and acquiring the tone score m of each Chinese character in the name;
step two: calculating score sum of athletesWherein m is i Tone assignment for representing the i-th kanji in the athlete's name;
step three: ranking the athletes according to the scoring sums, wherein the ranking is more rearward as the scoring sums are larger;
step four: starting from the first digit in the sequence, screening out pending sentences containing names of corresponding athletes through a regular expression;
step five: and repeating the first step to the fourth step, and screening out all pending sentences.
In another preferred implementation of the present invention, in the step one, a specific assigning process includes: the level of yin, level of yang, up-sounding and down-sounding are respectively assigned to 1, 2, 3 and 4.
It should be noted that the concept of the tone is quantized to make it more clear by assigning values to different tones separately.
In another preferred implementation of the present invention, in the third step, when there are two or more scoring sums that are the same, they are ranked according to the first pinyin of the name of the athlete.
In another preferred embodiment of the present invention, in the step S31, when there are two or more names of athletes in a sentence, the following steps are performed:
searching whether the sentence comprises the body event data or not through a regular expression;
when the sentence does not include the body event data, no subsequent processing is performed;
when the sentence includes the physical event data, prompting the statistics personnel to re-input the sentence and prompting the statistics personnel to adjust the voice input format to be the statistical format when the input voice is not recognized
Notably, when the sentence does not include the body event data, no subsequent steps are executed, so that the computing resources can be saved and the processing efficiency can be improved; when the sentence does not contain the body event data, the condition of error can be avoided by manually re-inputting, and the accuracy of data statistics is improved.
In another preferred embodiment of the present invention, in the step S32, when the athletic event data is not included in a certain pending sentence, the pending sentence does not perform the subsequent steps
It will be appreciated that this is done because the statistics personnel need only count the sports event data, and do not include sentences of sports event data, and do not need to be processed.
In another preferred embodiment of the present invention, when two or more sports event data are included in a pending sentence in step S32, the following steps are performed:
and obtaining the quantity a of the sports event data in the sentence, and generating a statistical formats of the sentence according to the sports event data in the sentence.
A athletic event data statistics system, comprising:
an initial module: determining statistics personnel of the current event, wherein the statistics personnel are staff responsible for counting sports event data, and the sports event data comprises athlete names, scores, attack aiding times, foul times and error times;
an input determination module: setting an acquisition period, and acquiring input voice in real time in the acquisition period, wherein the input voice is a voice signal sent by the statistics personnel, and the process of acquiring the input voice specifically comprises the following steps:
establishing a database, wherein voiceprints of statistical staff are stored in the database, establishing a voiceprint recognition model through a deep learning model, and training and verifying the voiceprint recognition model by using the database;
acquiring the voice signal in the acquisition period in real time, inputting the voice signal into a voiceprint recognition model, and acquiring input voice;
and a recording module: converting the input voice into a text format, acquiring all sentences in the text, and executing a scoring step:
s31: screening sentences containing the names of the athletes through regular expressions, defining the sentences as pending sentences, marking the position of the last character in the names of the athletes in the pending sentences, and defining the positions as pending positions;
s32: in the pending sentences, acquiring texts after the pending positions, searching whether the texts comprise sports event data or not through a regular expression, and generating statistical formats of the current pending sentences, wherein the statistical formats are player name-sports event data corresponding to the current pending sentences;
s33: repeating the steps S31-S32 to obtain the statistical format of all pending sentences;
and a sending module: generating a statistical table, wherein the statistical table comprises the score sum, the attack total times, the foul total times and the error total times of each athlete, and sending the statistical table to a statistical staff after the acquisition period is finished.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (8)
1. A method of sports event data statistics, comprising the steps of:
s1: determining statistics personnel of the current event, wherein the statistics personnel are staff responsible for counting sports event data, and the sports event data comprises athlete names, scores, attack aiding times, foul times and error times;
s2: setting an acquisition period, and acquiring input voice in real time in the acquisition period, wherein the input voice is a voice signal sent by the statistics personnel, and the process of acquiring the input voice specifically comprises the following steps:
establishing a database, wherein voiceprints of statistical staff are stored in the database, establishing a voiceprint recognition model through a deep learning model, and training and verifying the voiceprint recognition model by using the database;
acquiring the voice signal in the acquisition period in real time, inputting the voice signal into a voiceprint recognition model, and acquiring input voice;
s3: converting the input voice into a text format, acquiring all sentences in the text, and executing a scoring step:
s31: screening sentences containing the names of the athletes through regular expressions, defining the sentences as pending sentences, marking the position of the last character in the names of the athletes in the pending sentences, and defining the positions as pending positions;
s32: in the pending sentences, acquiring texts after the pending positions, searching whether the texts comprise sports event data or not through a regular expression, and generating statistical formats of the current pending sentences, wherein the statistical formats are player name-sports event data corresponding to the current pending sentences;
s33: repeating the steps S31-S32 to obtain the statistical format of all pending sentences;
s4: generating a statistical table, wherein the statistical table comprises the score sum, the attack total times, the foul total times and the error total times of each athlete, and sending the statistical table to a statistical staff after the acquisition period is finished.
2. The method of claim 1, wherein in step S31, the following steps are performed:
step one: acquiring the name of the athlete of the current event project, and acquiring the tone score m of each Chinese character in the name;
step two: calculating score sum of athletesWherein m is i Tone assignment for representing the i-th kanji in the athlete's name;
step three: ranking the athletes according to the scoring sums, wherein the ranking is more rearward as the scoring sums are larger;
step four: starting from the first digit in the sequence, screening out pending sentences containing names of corresponding athletes through a regular expression;
step five: and repeating the first step to the fourth step, and screening out all pending sentences.
3. The method of claim 2, wherein in the first step, the specific scoring process comprises: the level of yin, level of yang, up-sounding and down-sounding are respectively assigned to 1, 2, 3 and 4.
4. A method according to claim 2, wherein in the third step, when there are two or more scoring sums that are the same, they are ranked according to the first pinyin of the name of the athlete.
5. The method according to claim 1, wherein in the step S31, when there are two or more names of players in a sentence, the following steps are performed:
searching whether the sentence comprises the body event data or not through a regular expression;
when the sentence does not include the body event data, no subsequent processing is performed;
when the sentence includes the body event data, prompting a statistics person to re-input the sentence and prompting the statistics person to adjust the voice input format to be the statistical format when the input voice is not recognized.
6. A method according to claim 1, wherein in step S32, when the athletic event data is not included in a predetermined sentence, the predetermined sentence does not perform the following steps.
7. The method according to claim 1, wherein in the step S32, when two or more pieces of athletic event data are included in a predetermined sentence, the following steps are performed:
and obtaining the quantity a of the sports event data in the sentence, and generating a statistical formats of the sentence according to the sports event data in the sentence.
8. A system for accounting for athletic event data, comprising:
an initial module: determining statistics personnel of the current event, wherein the statistics personnel are staff responsible for counting sports event data, and the sports event data comprises athlete names, scores, attack aiding times, foul times and error times;
an input determination module: setting an acquisition period, and acquiring input voice in real time in the acquisition period, wherein the input voice is a voice signal sent by the statistics personnel, and the process of acquiring the input voice specifically comprises the following steps:
establishing a database, wherein voiceprints of statistical staff are stored in the database, establishing a voiceprint recognition model through a deep learning model, and training and verifying the voiceprint recognition model by using the database;
acquiring the voice signal in the acquisition period in real time, inputting the voice signal into a voiceprint recognition model, and acquiring input voice;
and a recording module: converting the input voice into a text format, acquiring all sentences in the text, and executing a scoring step:
s31: screening sentences containing the names of the athletes through regular expressions, defining the sentences as pending sentences, marking the position of the last character in the names of the athletes in the pending sentences, and defining the positions as pending positions;
s32: in the pending sentences, acquiring texts after the pending positions, searching whether the texts comprise sports event data or not through a regular expression, and generating statistical formats of the current pending sentences, wherein the statistical formats are player name-sports event data corresponding to the current pending sentences;
s33: repeating the steps S31-S32 to obtain the statistical format of all pending sentences;
and a sending module: generating a statistical table, wherein the statistical table comprises the score sum, the attack total times, the foul total times and the error total times of each athlete, and sending the statistical table to a statistical staff after the acquisition period is finished.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410107396.3A CN117648407B (en) | 2024-01-26 | 2024-01-26 | Sports event data statistics method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410107396.3A CN117648407B (en) | 2024-01-26 | 2024-01-26 | Sports event data statistics method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117648407A true CN117648407A (en) | 2024-03-05 |
CN117648407B CN117648407B (en) | 2024-04-16 |
Family
ID=90049783
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410107396.3A Active CN117648407B (en) | 2024-01-26 | 2024-01-26 | Sports event data statistics method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117648407B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020091723A1 (en) * | 2001-01-10 | 2002-07-11 | Talknsports Enterprises | System and method for collection, conversion and presentation of sports data |
CN107045496A (en) * | 2017-04-19 | 2017-08-15 | 畅捷通信息技术股份有限公司 | The error correction method and error correction device of text after speech recognition |
CN107315793A (en) * | 2017-06-14 | 2017-11-03 | 北京嘀哒时空网络科技有限公司 | A kind of voice-based competitive sports data statistical approach, system |
CN107485843A (en) * | 2017-09-26 | 2017-12-19 | 北京球友圈网络科技有限责任公司 | Count the method and device of ball sports information for the game |
CN108831440A (en) * | 2018-04-24 | 2018-11-16 | 中国地质大学(武汉) | A kind of vocal print noise-reduction method and system based on machine learning and deep learning |
CN109344292A (en) * | 2018-09-28 | 2019-02-15 | 百度在线网络技术(北京)有限公司 | Generation method, device, server and the storage medium of race score segment |
CN110717031A (en) * | 2019-10-15 | 2020-01-21 | 南京摄星智能科技有限公司 | Intelligent conference summary generation method and system |
CN116304035A (en) * | 2023-02-28 | 2023-06-23 | 中国司法大数据研究院有限公司 | Multi-notice multi-crime name relation extraction method and device in complex case |
-
2024
- 2024-01-26 CN CN202410107396.3A patent/CN117648407B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020091723A1 (en) * | 2001-01-10 | 2002-07-11 | Talknsports Enterprises | System and method for collection, conversion and presentation of sports data |
CN107045496A (en) * | 2017-04-19 | 2017-08-15 | 畅捷通信息技术股份有限公司 | The error correction method and error correction device of text after speech recognition |
CN107315793A (en) * | 2017-06-14 | 2017-11-03 | 北京嘀哒时空网络科技有限公司 | A kind of voice-based competitive sports data statistical approach, system |
CN107485843A (en) * | 2017-09-26 | 2017-12-19 | 北京球友圈网络科技有限责任公司 | Count the method and device of ball sports information for the game |
CN108831440A (en) * | 2018-04-24 | 2018-11-16 | 中国地质大学(武汉) | A kind of vocal print noise-reduction method and system based on machine learning and deep learning |
CN109344292A (en) * | 2018-09-28 | 2019-02-15 | 百度在线网络技术(北京)有限公司 | Generation method, device, server and the storage medium of race score segment |
CN110717031A (en) * | 2019-10-15 | 2020-01-21 | 南京摄星智能科技有限公司 | Intelligent conference summary generation method and system |
CN116304035A (en) * | 2023-02-28 | 2023-06-23 | 中国司法大数据研究院有限公司 | Multi-notice multi-crime name relation extraction method and device in complex case |
Non-Patent Citations (3)
Title |
---|
贺小雨: ""基于多属性特征的论文推荐系统设计与实现"", 《中国优秀硕士学位论文全文数据库信息科技辑(月刊)》, 15 January 2022 (2022-01-15), pages 4 * |
贺小雨: "基于多属性特征的论文推荐系统设计与实现", 《中国优秀硕士学位论文全文数据库信息科技辑(月刊)》, no. 01, 15 January 2022 (2022-01-15), pages 4 * |
高宇;: "实时数据对于体育赛事公共信号制作的重要性分析", 科技传播, no. 15, 8 August 2015 (2015-08-08) * |
Also Published As
Publication number | Publication date |
---|---|
CN117648407B (en) | 2024-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103886034B (en) | A kind of method and apparatus of inquiry input information that establishing index and matching user | |
CN109949799A (en) | A kind of semanteme analytic method and system | |
CN116206496B (en) | Oral english practice analysis compares system based on artificial intelligence | |
Pérez et al. | Objective-AoA norms for 175 names in Spanish: Relationships with other psycholinguistic variables, estimated AoA, and data from other languages | |
CN102314877A (en) | Voiceprint identification method for character content prompt | |
CN115188078A (en) | Ping-pong intelligent action training method based on voice interaction and attitude estimation | |
CN108319584A (en) | A kind of new word discovery method based on the microblogging class short text for improving FP-Growth algorithms | |
CN117648407B (en) | Sports event data statistics method and system | |
JP2006208644A (en) | Server system and method for measuring linguistic speaking ability | |
CN115700606A (en) | Grading method, grading device, grading equipment and computer readable storage medium | |
CN110188352B (en) | Text theme determining method and device, computing equipment and storage medium | |
CN116052491A (en) | Spoken language exercise interaction method, device, system, equipment and storage medium | |
CN116189851A (en) | Natural language processing-based athlete psychological consultation service system and method | |
CN112507115B (en) | Method and device for classifying emotion words in barrage text and storage medium | |
CN102034379B (en) | Chinese phonetic game learning chess | |
CN114328823A (en) | Database natural language query method and device, electronic equipment and storage medium | |
CN111243364A (en) | HanLP-based method for automatically scoring examination subjective questions of registered electrical engineers | |
CN114357144B (en) | Medical numerical extraction and understanding method and device based on small samples | |
CN114067787B (en) | Voice speech speed self-adaptive recognition system | |
CN113255324B (en) | Method for disambiguating inventor names in patent data | |
CN117131104B (en) | Intelligent question-drawing and winding method and device, electronic equipment and storage medium | |
CN117275319B (en) | Device for training language emphasis ability | |
CN118053595A (en) | Gymnasium movement data information management system and method based on digital gymnasium scene | |
CN111090742B (en) | Question-answer pair evaluation method, question-answer pair evaluation device, storage medium and equipment | |
CN113255330B (en) | Chinese spelling checking method based on character feature classifier and soft output |
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 |