新建 AipNlp:
AipNlp 是自然语言处理的 Python SDK 客户端,为使用自然语言处理的开发人员提供了一系列的交互方法。参考如下代码新建一个 AipNlp:
from aip import AipNlp
""" 你的 APPID AK SK """
APP_ID = '##########' #'你的 APP ID'
API_KEY = '##########' #'你的 Api key'
SECRET_KEY = '##########' #'你的 Secret key'
client = AipNlp(APP_ID, API_KEY, SECRET_KEY)
配置AipNlp:
如果用户需要配置 AipNlp 的网络请求参数(一般不需要配置),可以在构造 AipNlp 之后调用接口设置参数,目前只支持以下参数:
接口 | 说明 |
---|---|
setConnectionTimeoutInMillis | 建立连接的超时时间(单位:毫秒) |
setSocketTimeoutInMillis | 通过打开的连接传输数据的超时时间(单位:毫秒) |
接口说明:
词法分析:
词法分析接口向用户提供分词、词性标注、专名识别三大功能;能够识别出文本串中的基本词汇(分词),对这些词汇进行重组、标注组合后词汇的词性,并进一步识别出命名实体。
text = "百度是一家高科技公司"
""" 调用词法分析 """
client.lexer(text)
{'log_id': 3174179683102561622,
'text': '百度是一家高科技公司',
'items': [{'loc_details': [],
'byte_offset': 0,
'uri': '',
'pos': '',
'ne': 'ORG',
'item': '百度',
'basic_words': ['百度'],
'byte_length': 4,
'formal': ''},
{'loc_details': [],
'byte_offset': 4,
'uri': '',
'pos': 'v',
'ne': '',
'item': '是',
'basic_words': ['是'],
'byte_length': 2,
'formal': ''},
{'loc_details': [],
'byte_offset': 6,
'uri': '',
'pos': 'm',
'ne': '',
'item': '一家',
'basic_words': ['一', '家'],
'byte_length': 4,
'formal': ''},
{'loc_details': [],
'byte_offset': 10,
'uri': '',
'pos': 'n',
'ne': '',
'item': '高科技',
'basic_words': ['高', '科技'],
'byte_length': 6,
'formal': ''},
{'loc_details': [],
'byte_offset': 16,
'uri': '',
'pos': 'n',
'ne': '',
'item': '公司',
'basic_words': ['公司'],
'byte_length': 4,
'formal': ''}]}
词法分析(定制版)
text = "百度是一家高科技公司"
""" 调用词法分析(定制版)"""
client.lexerCustom(text)
{'log_id': 1030687273146384758,
'items': [{'loc_details': [],
'byte_offset': 0,
'uri': '',
'ne': 'ORG',
'basic_words': ['百度'],
'item': '百度',
'pos': '',
'byte_length': 4,
'formal': ''},
{'loc_details': [],
'byte_offset': 4,
'uri': '',
'ne': '',
'basic_words': ['是'],
'item': '是',
'pos': 'v',
'byte_length': 2,
'formal': ''},
{'loc_details': [],
'byte_offset': 6,
'uri': '',
'ne': '',
'basic_words': ['一', '家'],
'item': '一家',
'pos': 'm',
'byte_length': 4,
'formal': ''},
{'loc_details': [],
'byte_offset': 10,
'uri': '',
'ne': '',
'basic_words': ['高', '科技'],
'item': '高科技',
'pos': 'n',
'byte_length': 6,
'formal': ''},
{'loc_details': [],
'byte_offset': 16,
'uri': '',
'ne': '',
'basic_words': ['公司'],
'item': '公司',
'pos': 'n',
'byte_length': 4,
'formal': ''}],
'text': '百度是一家高科技公司'}
依存句法分析
依存句法分析接口可自动分析文本中的依存句法结构信息,哦拥句子中词与词之间的依存关系来表示词语的句法结构信息(如“主谓”、“动宾”、“定中”等结构关系),并用树状结构来表示整句的结构(如“主谓宾”、“定状补”等)。
text = "今天天气怎么样"
""" 调用依存句法分析 """
client.depParser(text)
""" 如果有可选参数 """
options = {}
options["mode"] = 1
""" 带参数调用依存句法分析 """
client.depParser(text, options)
{'log_id': 6738947376011839670,
'text': '今天天气怎么样',
'items': [{'postag': 't', 'head': 2, 'word': '今天', 'id': 1, 'deprel': 'ATT'},
{'postag': 'n', 'head': 3, 'word': '天气', 'id': 2, 'deprel': 'SBV'},
{'postag': 'r', 'head': 0, 'word': '怎么样', 'id': 3, 'deprel': 'HED'}]}
词向量表示
词向量表示接口提供中文词向量的查询功能。
word = "张飞"
""" 调用词向量表示 """
client.wordEmbedding(word)
{'log_id': 1696656248514338902,
'word': '张飞',
'vec': [-0.290384,
-0.276273,
0.302719,
0.7209,
0.108958,
0.553115,
-0.0877021,
0.359806,
0.0880146,
-0.189588,
0.244222,
-0.0651301,
0.0638421,
0.533272,
-0.00821664,
0.0375696,
-0.327892,
-0.46532,
0.865607,
0.623493,
-0.178252,
-0.0400714,
0.25975,
0.11109,
0.0953429,
0.101911,
-0.535927,
-0.0933478,
0.601825,
-0.321298,
0.631975,
0.0875886,
0.870735,
-0.269735,
-0.585102,
0.319081,
0.184684,
-0.720537,
-0.383718,
-0.0765072,
0.31901,
0.270633,
0.795086,
-0.203823,
-0.125412,
0.45416,
-0.172919,
0.295541,
-0.216173,
-0.430564,
0.0180166,
0.138979,
-0.277238,
0.741072,
0.190484,
-0.030923,
-0.0943274,
0.591492,
-0.418138,
-0.523783,
-0.227849,
0.366404,
-0.443689,
-0.125983,
0.0810465,
-0.40937,
-0.1809,
-0.391663,
0.184682,
0.176599,
0.296323,
0.263794,
0.148703,
0.121896,
0.267335,
-0.20897,
-0.000618858,
-0.258487,
0.284275,
0.115589,
-0.28355,
0.150706,
-0.220889,
-0.591039,
0.0290777,
-0.201643,
0.0797944,
0.488941,
0.831331,
-0.379756,
-0.139497,
0.2703,
0.504657,
-0.440968,
-0.1447,
-0.110457,
-0.0163559,
0.767792,
0.491371,
-0.549788,
0.205589,
0.362547,
0.445447,
0.114256,
-0.390303,
0.355757,
-0.35865,
0.309228,
-0.0702368,
0.0218542,
-0.20673,
0.18002,
0.0739457,
0.230891,
0.014336,
0.18294,
0.660368,
0.771709,
0.210481,
-0.366585,
-0.487737,
-0.392698,
0.165913,
0.0634584,
0.327222,
0.170312,
0.16333,
-0.0126046,
0.139614,
0.41918,
-0.151494,
0.317118,
-0.391317,
-0.673394,
-0.430471,
0.0830508,
-0.270076,
0.336409,
-0.218263,
0.417467,
0.595822,
-0.114509,
0.323514,
0.405187,
-0.144482,
-0.179517,
0.185674,
-0.161061,
0.0338107,
-0.290429,
-0.187511,
0.131024,
0.0655593,
-0.0429835,
0.249348,
0.470223,
0.439866,
0.191249,
-0.551478,
-0.0530808,
0.220113,
0.21264,
0.4053,
0.000986318,
0.431895,
-0.266691,
0.387755,
-0.176948,
0.790972,
-0.186954,
0.311339,
-0.847612,
0.0591855,
0.217022,
-0.40963,
0.0388994,
0.258638,
-0.0700524,
-0.517052,
0.0738539,
-0.0278234,
-0.0207165,
-0.64623,
-0.397078,
-0.512611,
0.240432,
0.631851,
-0.266089,
0.23193,
-0.335795,
0.48978,
0.101472,
0.112899,
0.0119656,
0.205143,
0.59687,
-0.139228,
0.2366,
-0.0448019,
-0.463323,
0.136911,
0.245667,
-0.531107,
-0.203959,
0.437006,
0.0385832,
-0.475222,
0.152122,
-0.183256,
0.147781,
0.976636,
-0.268798,
0.0467436,
0.398612,
0.726595,
0.0641848,
0.442981,
0.392992,
0.277279,
0.191023,
0.540712,
0.041807,
0.521223,
0.494714,
-0.114315,
-0.623037,
0.503307,
0.16223,
-0.0109138,
-0.0030869,
-0.0127418,
0.0324629,
0.257331,
-0.724175,
0.071035,
0.293041,
-0.142676,
0.216268,
0.217721,
0.150594,
0.524261,
0.136377,
-0.26703,
0.143736,
0.377088,
0.0852308,
-0.248864,
-0.2864,
0.336949,
0.0106289,
0.142447,
0.0830073,
0.00827009,
0.170654,
-0.0537858,
0.66666,
-0.167388,
-0.00478372,
0.370992,
-0.420722,
-0.0163072,
-0.224316,
0.900274,
-0.0618271,
0.0933983,
-0.138376,
0.0352047,
0.133874,
-0.274968,
-0.1037,
0.056145,
0.283046,
-0.222181,
0.0843009,
0.201509,
0.0759472,
0.430465,
0.279714,
-0.0762712,
0.0291045,
0.0666021,
0.389999,
-0.0268815,
0.35655,
0.167335,
0.555981,
0.277015,
0.370779,
-0.249201,
-0.153099,
0.15063,
0.59068,
0.144961,
-0.36857,
0.38433,
-0.627967,
0.460143,
0.207135,
-0.270095,
-0.175896,
0.132773,
0.260412,
-0.0316362,
-0.511945,
-0.014644,
-0.338383,
0.513172,
0.273772,
-0.245957,
-0.484812,
0.479638,
-0.781593,
-0.692486,
0.269043,
0.48944,
0.151724,
-0.109521,
0.0716606,
0.454819,
-0.641453,
-0.28264,
-0.0844294,
0.0127063,
-0.0473483,
-0.0599927,
0.0715608,
-0.562256,
0.215818,
-0.207625,
-0.0960898,
0.0344254,
-0.0852497,
-0.119984,
0.296039,
-0.595229,
0.253829,
-0.111723,
0.411277,
0.101737,
-0.0322796,
0.345638,
0.0965107,
0.083087,
0.291633,
-0.091778,
-0.0279783,
-0.108174,
-0.300271,
-0.541914,
0.197143,
0.631338,
0.479441,
0.0369768,
0.451288,
-0.127012,
-0.639879,
0.0512995,
0.273387,
-0.418342,
-0.45064,
-0.1239,
-0.595654,
0.31378,
-0.35008,
-0.0134738,
0.476063,
0.0309964,
-0.0264222,
-0.4704,
0.201462,
0.967353,
-0.0587739,
-0.221851,
-0.221493,
-0.319194,
0.321394,
0.176416,
0.0173751,
-0.0174415,
0.339173,
-0.0516278,
-0.255842,
-0.283161,
-0.017094,
-0.138473,
0.271638,
0.496162,
0.519359,
-0.00602108,
0.459303,
0.295921,
0.27062,
0.753482,
0.0583323,
0.181312,
-0.106313,
0.646242,
-0.00311025,
-0.163957,
0.182659,
-0.0996339,
0.272461,
0.301206,
0.35085,
0.37463,
-0.155242,
0.281236,
-0.294234,
0.00533482,
-0.00310824,
0.0731524,
-0.394956,
0.452704,
0.000153456,
-0.0800992,
-0.0785606,
-0.439399,
-0.575366,
-0.216206,
-0.212303,
-0.624662,
0.0487097,
-0.15867,
0.278319,
-0.21006,
0.786678,
0.23844,
0.189342,
0.108299,
-0.511393,
0.405482,
-0.161949,
0.212671,
-0.379168,
-0.0637337,
0.13583,
0.0522022,
0.072762,
-0.11513,
-0.647886,
0.112957,
0.147099,
-0.156163,
-0.127035,
0.145647,
0.182698,
0.482085,
-0.0702394,
-0.0172681,
-0.24563,
-0.0392392,
-0.491031,
-0.19934,
0.132408,
0.285179,
0.40498,
0.134263,
0.262012,
0.142867,
-0.147229,
-0.268257,
0.1726,
0.476211,
-0.836967,
0.568796,
0.077607,
-0.510508,
0.0675741,
-0.681589,
0.100888,
-0.326709,
0.266345,
-0.397411,
-0.644215,
-0.13274,
-0.354817,
-0.558334,
-0.114178,
-0.0940336,
0.235152,
-0.554642,
0.382976,
-0.274543,
-0.105513,
-0.409024,
-0.0281389,
-0.350335,
-0.773656,
0.602614,
0.0406916,
-0.566817,
0.100671,
0.0793555,
0.176259,
0.218086,
0.654524,
-0.109966,
0.157835,
-0.214399,
0.166806,
0.297687,
-0.526347,
0.330715,
-0.223834,
0.354683,
0.164879,
-0.060529,
0.208646,
-0.347635,
-0.386788,
-0.434064,
-0.448538,
0.106584,
-0.137211,
-0.821776,
0.448596,
0.55277,
-0.486275,
0.0597583,
0.108438,
0.0167387,
-0.205475,
-0.367478,
0.0528088,
0.191489,
0.308181,
0.124091,
0.0241138,
0.332369,
-0.418433,
0.609042,
-0.564987,
-0.0275926,
-0.190715,
0.114899,
0.0137452,
0.00163973,
0.0747787,
0.219737,
0.0336625,
0.0256406,
-0.14083,
-0.0510848,
0.280421,
-0.0751052,
-0.195839,
0.217633,
-0.110681,
-0.692188,
-0.516287,
0.0406127,
0.514706,
0.461349,
0.31112,
-0.505281,
-0.209302,
-0.478191,
-0.159178,
0.262902,
0.215158,
-0.0384547,
-0.0301001,
-0.68696,
0.333097,
0.387189,
-0.397549,
-0.389793,
-0.326927,
-0.426165,
-0.249444,
-0.287807,
-0.358692,
0.344935,
-0.22274,
-0.12828,
-0.0673532,
-0.0972766,
-0.227617,
-0.248091,
-0.0705791,
0.63178,
-0.759731,
-0.368149,
0.578806,
0.280523,
-0.0312885,
-0.516321,
-0.308148,
-0.463663,
-1.11399,
0.299133,
0.324969,
-0.0922515,
-0.223782,
0.0757393,
0.0956187,
0.307651,
0.274788,
-0.495276,
0.305883,
0.0228269,
0.437532,
-0.260021,
-0.36529,
-0.122708,
-0.175827,
0.146148,
0.143242,
-0.142164,
-0.0918094,
-0.415535,
-0.0301366,
-0.295545,
-0.618801,
0.175826,
-0.756559,
-0.128965,
0.0491931,
0.733814,
-0.0347257,
-0.460981,
-0.540235,
0.138612,
-0.353038,
-0.0671316,
0.0149887,
-0.503586,
0.0874566,
0.441919,
0.0776407,
-0.272449,
-0.0997288,
-0.44766,
-0.216144,
-0.00963199,
0.0527866,
-0.0218697,
0.180018,
0.164696,
0.724876,
0.136289,
0.225619,
-0.161481,
0.165889,
0.857903,
-0.15784,
0.186857,
-0.662843,
-0.558884,
-0.0192077,
0.00818205,
-0.0243429,
-0.217057,
-0.455544,
0.00163086,
-0.466992,
0.113344,
-0.174208,
0.251834,
-0.0775733,
0.102453,
0.258227,
-0.145805,
0.00610516,
-0.173767,
0.129026,
-0.132582,
-0.148301,
-0.458603,
0.367434,
-0.382593,
0.116882,
-0.0928457,
0.276499,
0.180621,
0.351536,
0.353009,
-0.31789,
-0.0245226,
-0.189822,
-0.705618,
-0.0623819,
-0.68237,
0.027945,
0.0396841,
-0.081132,
0.414828,
0.251657,
-0.193545,
-0.0149343,
0.0925272,
-0.12489,
-0.458534,
0.55974,
0.277349,
0.113657,
0.574713,
-0.198563,
0.905217,
0.101096,
0.0367823,
-0.120045,
0.278173,
-0.191525,
-0.0414615,
-0.105125,
-0.78052,
-0.448668,
0.30789,
0.497319,
-0.398035,
-0.55494,
-0.272399,
-0.102899,
-0.281833,
-0.262621,
0.138731,
-0.444618,
0.497306,
-0.275449,
-0.0123345,
-0.120426,
0.491484,
-0.402516,
-0.288962,
0.387392,
-0.144125,
0.838843,
-0.236083,
0.227957,
0.418015,
0.510442,
0.0841282,
-0.544343,
-0.0525509,
-0.0398014,
0.381329,
0.281488,
-0.403923,
-0.210186,
-0.53414,
0.0852807,
-0.345891,
-0.294183,
1.17415,
-0.023307,
-0.828112,
0.0523113,
-0.0824572,
0.317031,
-0.543952,
-0.699134,
-0.278506,
-0.576854,
0.434733,
-0.267847,
-0.570456,
-0.017377,
0.645807,
-0.917205,
0.441665,
-0.393248,
0.0631595,
-0.386241,
0.0413631,
0.0191933,
-0.474338,
-0.113288,
0.400757,
-0.0247571,
-0.348845,
-0.0123555,
0.25809,
0.427283,
0.245173,
-0.294317,
0.159206,
0.118759,
0.273828,
0.643573,
0.0927131,
-0.265129,
0.233232,
-0.138332,
-0.136015,
-0.673727,
0.684253,
-0.0585586,
-0.327816,
-0.716404,
-0.58116,
0.0275417,
-0.0388521,
0.0237589,
-0.277684,
0.0602299,
0.209622,
0.0348703,
0.327143,
0.24981,
-0.251077,
-0.455329,
0.396863,
-0.0570048,
-0.265072,
-0.0683558,
0.0132361,
0.273579,
-0.366049,
0.615134,
-0.103124,
0.481334,
-0.746339,
-0.0640788,
-0.484396,
-0.00114065,
0.366753,
0.0240541,
0.439156,
0.159546,
-0.0506753,
0.0468946,
0.43076,
0.602602,
0.0107401,
1.19797,
0.44314,
-0.698443,
-0.336827,
0.0258312,
0.172399,
0.305746,
-0.150144,
0.0203008,
0.326867,
-0.644517,
0.0156665,
0.13351,
-0.23441,
-0.293748,
-0.0695886,
-0.477291,
0.281291,
-0.755484,
0.74025,
-0.552702,
0.381103,
0.164566,
-0.15145,
-0.728736,
0.448275,
0.0725737,
0.116212,
0.210402,
0.691626,
0.0265872,
-0.448584,
0.244172,
-0.245309,
0.139035,
0.0288716,
-0.364476,
-0.0426868,
-0.21928,
-0.742586,
-0.0932949,
-0.193005,
0.0303013,
-0.76493,
0.0455655,
-0.608174,
0.255099,
0.0151615,
0.0139608,
0.0158675,
-0.3893,
0.373225,
0.250462,
0.0276716,
-0.0752877,
-0.0127418,
-0.435184,
-0.0627005,
-0.400453,
-0.147969,
0.235518,
0.181853,
-0.339577,
0.553451,
0.00837407,
-0.248918,
-0.136399,
-0.354747,
-0.350052,
0.220699,
-0.183795,
0.784734,
0.395384,
-0.315588,
0.0276707,
0.0840118,
0.254402,
0.0226935,
-0.483695,
-0.075312,
0.402732,
-0.0151023,
0.166692,
0.65539,
0.467999,
0.192916,
-0.429285,
-0.349553,
0.626268,
0.153931,
0.0643198,
0.292859,
0.156136,
-0.064216,
0.0490229,
0.147063,
0.151404,
-0.701247,
-0.0486219,
0.0359798,
-0.307433,
-0.254073,
-0.0960998,
0.386864,
-0.100606,
-0.0278402,
0.27646,
-0.373706,
0.244237,
0.445031,
-0.0736471,
0.681565,
-0.361913,
0.107957,
-0.0310045,
-0.0797901,
-0.0512583,
-0.560119,
0.0451696,
-0.112058,
0.010503,
0.456464,
0.180504,
0.187385,
-0.492449,
0.0517042,
-0.269497,
-0.0741519,
-0.134895,
-0.102614,
0.0668148,
-0.498746,
0.386095,
-0.131642,
-0.208304,
-0.0341324,
-0.151889,
0.341949,
0.0420371,
-0.116241,
0.440811,
-0.108852,
0.134327,
0.0777457,
0.488344,
0.0472591,
0.697291,
-0.580174,
0.101828,
0.131381,
-0.192425,
-0.317998,
0.122801,
0.0694366,
0.21801,
-0.0429734,
-0.136425,
0.437184,
-0.11753,
0.344893,
0.24043,
0.0306901,
-0.422333,
-0.146097,
0.520181,
0.0972754,
-0.186103,
-0.0766742,
-0.745162,
0.364611,
0.186148,
-0.250859,
0.243429,
-0.251991,
-0.424686,
...]}
DNN 语言模型
中文 DNN 语言模型接口用于输出切词结果并给出每个词在句子中的概率值,判断一句话是否符合语言表达习惯。
text = "床前明月光"
""" 调用 DNN 语言模型 """
client.dnnlm(text)
{'log_id': 8461893498410162902,
'text': '床前明月光',
'items': [{'word': '床', 'prob': 3.85273e-05},
{'word': '前', 'prob': 0.0289018},
{'word': '明月', 'prob': 0.0284406},
{'word': '光', 'prob': 0.808029}],
'ppl': 79.0651}
词意相似度
输入两个词,得到两个词的相似度结果。
word1 = "北京"
word2 = "上海"
""" 调用词义相似度 """
client.wordSimEmbedding(word1, word2)
""" 如果有可选参数 """
options = {}
options["mode"] = 0
""" 带参数调用词义相似度 """
client.wordSimEmbedding(word1, word2, options)
{'log_id': 1841062063069490934,
'error_code': 282004,
'error_msg': 'invalid parameter(s)'}
短文本相似度
text1 = "浙富股份"
text2 = "万事通自考网"
""" 调用短文本相似度 """
client.simnet(text1, text2)
""" 如果有可选参数 """
options = {}
options["model"] = "CNN"
""" 带参数调用短文本相似度 """
client.simnet(text1, text2, options)
{'log_id': 8759613961966585046,
'texts': {'text_2': '万事通自考网', 'text_1': '浙富股份'},
'score': 0.0549339}
评论观点抽取
评论观点抽取接口用来提取一条评论句子的关注点和评论观点,并输出评论观点标签以及评论观点极性。
text = "三星电脑电池不给力"
""" 调用评论观点抽取 """
client.commentTag(text)
""" 如果有可选参数 """
options = {}
options["type"] = 13
""" 带参数调用评论观点抽取 """
client.commentTag(text, options)
{'log_id': 8426923826378164630,
'items': [{'sentiment': 0,
'abstract': '三星电脑<span>电池不给力</span>',
'prop': '电池',
'begin_pos': 8,
'end_pos': 18,
'adj': '不给力'}]}
情感倾向分析
对包含主观观点信息的文本进行情感极性类别(积极、消极、中性)的判断,并给出相应的置信度。
text = "苹果是一家伟大公司"
""" 调用情感倾向分析 """
client.sentimentClassify(text)
{'log_id': 7415487462125078582,
'text': '苹果是一家伟大公司',
'items': [{'positive_prob': 0.691839,
'confidence': 0.315198,
'negative_prob': 0.308161,
'sentiment': 2}]}
文章标签
文章标签服务能够针对网络各类媒体文章进行快速的内容理解,根据输入含有标题的文章,输出多个内容标签以及对应的置信度,用于个性化推荐、相似文章聚合、文本内容分析等场景。
title = "iphone手机出现“白苹果”原因及解决办法,用苹果手机的可以看下"
content = "如果下面的方法还是没有解决你的问题建议来我们门店看下成都市锦江区红星路三段99号银石广场24层01室。"
""" 调用文章标签 """
client.keyword(title, content)
{'log_id': 4313909132996888022,
'items': [{'score': 0.99775, 'tag': 'iphone'},
{'score': 0.862602, 'tag': '手机'},
{'score': 0.845657, 'tag': '苹果'},
{'score': 0.837886, 'tag': '苹果公司'},
{'score': 0.811601, 'tag': '白苹果'},
{'score': 0.797911, 'tag': '数码'}]}
文章分类
对文章按照内容类型进行自动分类,首批支持娱乐、体育、科技等26个主流内容类型,文本内容分析等应用提供基础技术支持。
title = "欧洲冠军杯足球赛"
content = "欧洲冠军联赛是欧洲足球协会联盟主办的年度足球比赛,代表欧洲俱乐部足球最高荣誉和水平,被认为是全世界最高素质、最具影响力以及最高水平的俱乐部赛事,亦是世界上奖金最高的足球赛事和体育赛事之一。"
""" 调用文章分类 """
client.topic(title, content)
{'log_id': 2207187729196380118,
'item': {'lv2_tag_list': [{'score': 0.915631, 'tag': '足球'},
{'score': 0.803507, 'tag': '国际足球'},
{'score': 0.77813, 'tag': '英超'}],
'lv1_tag_list': [{'score': 0.830915, 'tag': '体育'}]}}
文本纠错
识别输入文本中有错误的片段,提示错误并给出正确的文本结果。支持短文本、长文本、语音等内容的错误识别,纠错是搜索引擎、语音识别、内容审查等功能更好运行的基础模块之一。
text = "百度是一家仁工智能公司"
""" 调用文本纠错 """
client.ecnet(text)
{'log_id': 4819268271360271574,
'item': {'vec_fragment': [{'ori_frag': '仁工',
'begin_pos': 10,
'correct_frag': '人工',
'end_pos': 14}],
'score': 0.529867,
'correct_query': '百度是一家人工智能公司'},
'text': '百度是一家仁工智能公司'}
对话情绪识别接口
针对用户日常沟通文本背后所蕴含情绪的一种直观检测,可自动识别出当前会话者所表现出的情绪类别及其置信度,可以帮助企业更全面地把握产品服务质量、监控客户服务质量。
text = "本来今天高高兴兴"
""" 调用对话情绪识别接口 """
client.emotion(text)
""" 如果有可选参数 """
options = {}
options["scene"] = "talk"
""" 带参数调用对话情绪识别接口 """
client.emotion(text, options)
{'log_id': 901856600521512694,
'text': '本来今天高高兴兴',
'items': [{'subitems': [{'prob': 0.501008, 'label': 'happy'}],
'replies': ['你的笑声真欢乐'],
'prob': 0.501008,
'label': 'optimistic'},
{'subitems': [], 'replies': [], 'prob': 0.49872, 'label': 'neutral'},
{'subitems': [],
'replies': [],
'prob': 0.000272128,
'label': 'pessimistic'}]}
新闻摘要接口
自动抽取新闻文本中的关键信息,进而生成指定长度的新闻摘要。
content = "麻省理工学院的研究团队为无人机在仓库中使用RFID技术进行库存查找等工作,创造了一种..."
maxSummaryLen = 300
""" 调用新闻摘要接口 """
client.newsSummary(content, maxSummaryLen);
""" 如果有可选参数 """
options = {}
options["title"] = "标题"
""" 带参数调用新闻摘要接口 """
client.newsSummary(content, maxSummaryLen, options)
{'error_code': 6, 'error_msg': 'No permission to access data'}