CN112364603B - Index code generation method, device, equipment and storage medium - Google Patents
Index code generation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112364603B CN112364603B CN202011298686.9A CN202011298686A CN112364603B CN 112364603 B CN112364603 B CN 112364603B CN 202011298686 A CN202011298686 A CN 202011298686A CN 112364603 B CN112364603 B CN 112364603B
- Authority
- CN
- China
- Prior art keywords
- index
- dimension
- measurement
- indexes
- code
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/126—Character encoding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of big data and discloses an index code generation method, an index code generation device, index code generation equipment and a storage medium. The method comprises the following steps: acquiring index names of service demands; carrying out semantic word segmentation processing on the index names by adopting a preset natural language processing model to obtain a plurality of index words; acquiring a multi-dimension index table and an index dimension coding mapping table, comparing the multi-dimension index table with each index vocabulary, and determining dimension indexes and measurement indexes corresponding to each index vocabulary; searching for each dimension index and the atomic index code corresponding to each measurement index from the index dimension code mapping table, and sequencing each atomic index code according to a preset rule; and splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index code of the demand index name. The present invention also relates to blockchain techniques, the index encoding being stored in the blockchain. The invention improves the standardization degree of the business index management framework.
Description
Technical Field
The present invention relates to the field of big data, and in particular, to a method, an apparatus, a device, and a storage medium for generating an index code.
Background
The index refers to a quantized measurement value after the service unit is subdivided, so that the service target can be described, measured and disassembled, and the index is used as the combination of service and data, is the basis of data statistics and is the basis for quantizing the service effect. On the basis of standard definition and management of indexes, the construction of a bottom fact table and a dimension table can be promoted, and the uniqueness of data sources and the unification of calculation caliber of data statistics are ensured. Meanwhile, by combining indexes and modifier words, service personnel can conveniently analyze and use data in a self-service mode, the data acquisition efficiency is reduced, and therefore valuable conclusions are generated, decision making is assisted, and the value of the data is fully exerted.
At present, business indexes are managed in a vocabulary description mode, and for different department management units of the same company, the management dimensions, index vocabularies, statistical sources, statistical modes, statistical time nodes and the like used are different due to the fact that the related fields are different, so that the following problems exist: for the same business scene, each department can use different indexes to measure; for the calculation of the same index, statistics is carried out at different time points, and the statistical sources and modes have differences; calculating the difference of caliber; in summary, the existing business index management architecture has the problem of low standardization level.
Disclosure of Invention
The invention mainly aims to solve the technical problem of low standardization degree of the existing business index management architecture.
The first aspect of the present invention provides an index code generating method, including:
acquiring index names of service demands;
performing semantic word segmentation on the index names by adopting a preset natural language processing model to obtain a plurality of index words;
acquiring a multi-dimensional index table and an index dimension coding mapping table, acquiring the multi-dimensional index table and the index dimension coding mapping table, and screening dimension indexes and measurement indexes corresponding to each index vocabulary from the multi-dimensional index table;
searching the dimension indexes and the atomic index codes corresponding to the measurement indexes from the index dimension code mapping table, and sequencing the atomic index codes according to a preset rule;
and splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index code of the demand index name.
Optionally, in a first implementation manner of the first aspect of the present invention, before the obtaining the index name of the service requirement, the method further includes:
Acquiring historical service information, and carrying out abstract processing on the historical service information to obtain a plurality of characteristic words;
clustering the feature words by adopting a preset clustering model to obtain a plurality of dimension indexes with different dimensions and one or more measurement indexes;
fixing the one or more measurement indexes, and combining the dimension indexes based on the affiliated dimension of the dimension indexes to obtain a corresponding multi-dimension index table;
and coding the dimension index and the measurement index to obtain a corresponding atomic index code, and creating an index dimension code mapping table based on the atomic index code.
Optionally, in a second implementation manner of the first aspect of the present invention, the screening the dimension index and the measurement index corresponding to each index vocabulary from the multidimensional index table includes:
extracting identification information of index types in the multi-dimensional index table, and determining a first type index and a second type index in the multi-dimensional index table based on the identification information;
matching the index vocabulary with the first type index, and determining one or more dimension indexes contained in the index vocabulary;
And matching the screened index vocabulary with the second type index, and determining one or more measurement indexes contained in the index vocabulary.
Optionally, in a third implementation manner of the first aspect of the present invention, before the filtering the dimension index and the metric index corresponding to each index vocabulary from the multi-dimension index table, the method further includes:
judging whether the multidimensional index table contains dimension indexes and measurement indexes corresponding to all index vocabularies or not;
if the index vocabulary is not contained, generating reminding information based on the index vocabulary not contained, so as to prompt a user to perfect the multi-dimensional index table.
Optionally, in a fourth implementation manner of the first aspect of the present invention, after the obtaining the index name of the service requirement, the method further includes:
determining the measurement caliber of the index name, and judging whether the measurement caliber of the index name meets the preset measurement caliber specification;
if yes, carrying out vocabulary entity standardization processing on the index names by adopting a preset character recognition library so as to accord with word segmentation processing rules of a preset natural language processing model.
Optionally, in a fifth implementation manner of the first aspect of the present invention, after the splicing the atomic index codes according to the sorting order of the atomic index codes, the method further includes:
Acquiring a plurality of measurement data corresponding to the service demand based on each index code after the index codes of all index names in the service demand are obtained;
and generating a business report according to the measurement data and displaying the business report.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the index code is further stored in a blockchain.
The second aspect of the present invention provides an index code generating device, including:
the acquisition module is used for acquiring index names of service demands;
the word segmentation module is used for carrying out semantic word segmentation on the index names by adopting a preset natural language processing model to obtain a plurality of index words;
the screening module is used for acquiring a multi-dimension index table and an index dimension coding mapping table, and screening dimension indexes and measurement indexes corresponding to each index vocabulary from the multi-dimension index table;
the searching module is used for searching the dimension indexes and the atomic index codes corresponding to the measurement indexes from the index dimension code mapping table, and sequencing the atomic index codes according to a preset rule;
and the splicing module is used for splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index code of the demand index name.
Optionally, in a first implementation manner of the second aspect of the present invention, the index code generating device further includes:
the abstract processing module is used for acquiring historical service information and carrying out abstract processing on the historical service information to obtain a plurality of feature words;
the clustering module is used for clustering the feature words by adopting a preset clustering model to obtain a plurality of dimension indexes with different dimensions and one or more measurement indexes;
the combination module is used for fixing the one or more measurement indexes, and combining the dimension indexes based on the affiliated dimension of the dimension indexes to obtain a corresponding multi-dimensional index table;
and the coding module is used for coding the dimension index and the measurement index to obtain a corresponding atomic index code, and creating an index dimension code mapping table based on the atomic index code.
Optionally, in a second implementation manner of the second aspect of the present invention, the screening module includes:
the extraction unit is used for extracting the identification information of the index type in the multi-dimensional index table and determining a first type index and a second type index in the multi-dimensional index table based on the identification information;
The first matching unit is used for matching the index vocabulary with the first type index and determining one or more dimension indexes contained in the index vocabulary;
and the second matching unit is used for matching the screened index vocabulary with the second type of index and determining one or more measurement indexes contained in the index vocabulary.
Optionally, in a third implementation manner of the first aspect of the present invention, the index code generating device further includes:
the first judging module is used for judging whether the multidimensional index table contains dimension indexes and measurement indexes corresponding to all index vocabularies;
and the generating module is used for generating reminding information based on the index vocabulary which is not included if the dimension index and the measurement index corresponding to all the index vocabulary are not included in the multi-dimensional index table so as to prompt a user to perfect the multi-dimensional index table.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the index code generating device further includes:
the second judging module is used for determining the measurement caliber of the index name and judging whether the measurement caliber of the index name meets the preset measurement caliber specification;
And the standardized processing module is used for carrying out vocabulary entity standardized processing on the index name by adopting a preset character recognition library if the measurement caliber of the index name meets the preset measurement caliber specification so as to meet the word segmentation processing rule of a preset natural language processing model.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the index code generating device further includes a report display module, configured to obtain, after obtaining index codes of all index names in the service requirement, based on the index codes, a plurality of metric data corresponding to the service requirement; and generating a business report according to the measurement data and displaying the business report.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the index code is further stored in a blockchain.
A third aspect of the present invention provides an index code generation apparatus, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the indicator code generation apparatus to perform the indicator code generation method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the above-described index code generation method.
In the technical scheme provided by the invention, an index management method based on natural language processing is provided. The invention extracts a plurality of index vocabularies of index names by carrying out semantic word segmentation processing on the acquired index names and adopting a natural language processing model; screening dimension indexes and measurement indexes of each index vocabulary through a pre-constructed multi-dimension index table, and determining the atomic index codes of each dimension index and measurement index through an index dimension code mapping table; by sequencing and splicing preset rules, index codes with unique sequencing sequences are obtained, ambiguity generated by sequencing of different atomic index codes is avoided, the index codes are used for representing corresponding index names, and the standardization degree of a business index management architecture is increased.
Drawings
FIG. 1 is a schematic diagram of a first embodiment of a method for generating index codes in an embodiment of the present invention;
FIG. 2 is a diagram of a second embodiment of a method for generating index codes in accordance with an embodiment of the present invention;
FIG. 3 is a diagram illustrating a third embodiment of a method for generating index codes according to an embodiment of the present invention;
FIG. 4 is a diagram of a fourth embodiment of a method for generating index codes in an embodiment of the present invention;
FIG. 5 is a schematic diagram of an embodiment of an index code generating device according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of another embodiment of an index code generating device according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an embodiment of an apparatus for generating an index code according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method, a device, equipment and a storage medium for generating index codes, which are used for acquiring index names of service demands; carrying out semantic word segmentation processing on the index names by adopting a preset natural language processing model to obtain a plurality of index words; acquiring a multi-dimension index table and an index dimension coding mapping table, comparing the multi-dimension index table with each index vocabulary, and determining dimension indexes and measurement indexes corresponding to each index vocabulary; searching for each dimension index and the atomic index code corresponding to each measurement index from the index dimension code mapping table, and sequencing each atomic index code according to a preset rule; and splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index code of the demand index name. The invention improves the standardization degree of the business index management framework.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For ease of understanding, a specific flow of an embodiment of the present invention is described below with reference to fig. 1, where a first embodiment of a method for generating a code in an embodiment of the present invention includes:
101. acquiring index names of service demands;
it is to be understood that the execution subject of the present invention may be the index code generating device, or may be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example. It should be emphasized that, to further ensure the privacy and security of the index code, the index code may also be stored in a node of a blockchain.
In this embodiment, the index name is used to describe a business process, for example, "sales amount of the product a in the B time period and the C channel" is an index name. The index name is manually input by the user through the front end according to the service requirement and is received by the server.
102. Performing semantic word segmentation on the index names by adopting a preset natural language processing model to obtain a plurality of index words;
in this embodiment, for semantic word segmentation of an index name by a natural language processing model, first, a plurality of common word segments of the index name are extracted by defining word segment lengths; then text cleaning is carried out on the plurality of segmented words, and segmented words without entity meaning and rare words are screened out; and classifying each word after text cleaning by adopting a characteristic template in a preset natural language processing model to obtain an index word and a non-index word, wherein the characteristic template contains corresponding characteristics of the index word, such as xxxx years, xx, month xx, day, x quarter and other characteristics of the time index word.
103. Acquiring a multi-dimensional index table and an index dimension coding mapping table, acquiring the multi-dimensional index table and the index dimension coding mapping table, and screening dimension indexes and measurement indexes corresponding to each index vocabulary from the multi-dimensional index table;
In this embodiment, the multidimensional index table is composed of a plurality of dimension indexes and measurement indexes, and includes all basic data that can be analyzed in an enterprise; the dimension index represents the angle of data analysis, the sales channel can comprise on-line sales, off-line sales, agency sales and the like, and the traffic dimension can be formed by aviation, sea, highway and railway; the metrics represent data presented by the analysis, such as sales amount, sales quantity, net profit, etc.
The multi-dimension index table contains a plurality of dimension categories, such as product type, sales channel, analysis time range, sales amount, etc., one dimension category may contain a plurality of dimension members, such as time dimension, may contain a first quarter, a second quarter, a third quarter, a fourth quarter; dimension members may be defined by different dimension hierarchies, such as using "year, month, day" and "year, quarter, month" to define different dimension members; the dimension hierarchy may also include multiple dimension levels, such as three levels including year, month, and day for "year, month, and day", and different levels have parent and child overlay relationships.
The measurement index is a special dimension in the multi-dimension index table, and all other dimension indexes need to aggregate and analyze data by taking the measurement index as the direction. For example, the measurement index is sales amount, and the sales amount of the product A in the time period B and the sales amount of the product C in the time period A, the sales amount of the product B in the time period E and the area C can be analyzed, wherein the sales amount is fixed.
104. Searching the dimension indexes and the atomic index codes corresponding to the measurement indexes from the index dimension code mapping table, and sequencing the atomic index codes according to a preset rule;
in this embodiment, the dimension index and the measurement index in the multidimensional index table are both represented in the form of an atomic index code, and are stored in a unified manner in the form of an index dimension code mapping table; and then, directly adopting the index dimension coding mapping table to search each dimension index of the target index name and the atomic index code corresponding to each measurement index.
The method can adopt fields with different specifications to represent dimension indexes and measurement indexes with different dimensions, for example, an atomic index code with a field with A specification to represent the time dimension, a field with B specification to represent the atomic index code with a product dimension, and a field with C specification to represent the atomic index code with a channel dimension; the A01 field identifies the current day, the A02 field identifies the current month, the A03 field identifies the current quarter, the B01 field identifies the insurance product, the B02 field identifies the financial product, the C01 field identifies the on-line sales channel, the C02 field identifies the off-line sales channel, and the C03 field identifies the proxy sales channel.
105. And splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index code of the demand index name.
In this embodiment, the sorting order of the atomic index codes corresponding to each dimension type is first specified, so as to prevent the ambiguity of the index codes due to different splicing orders when the atomic index codes are spliced, for example, a01B02C03 and B02C03a01 indicate the same index name, but indicate the index codes by using different index codes, and the meanings of the index codes are different.
In this embodiment, after index codes of all index names in the service requirement are obtained, a plurality of metric data corresponding to the service requirement are obtained based on the index codes; and generating a business report according to the measurement data and displaying the business report. The measurement data is a data value corresponding to the measurement index, and the selection of the measurement data depends on the dimension index.
For example, the premium of all the car insurance on the same day can be obtained through the index code A, the premium of all the car insurance on the same month can be obtained through the index code B, the premium of all the car insurance on the same year and the same month can be obtained through the index code C, and then the premium on the same day and the same month on the same year can be obtained through the index code A, and then the service report of the same date and the service report of the same month on the same year and the same month on the same year can be generated.
The embodiment of the invention provides an index management method based on natural language processing. The invention extracts a plurality of index vocabularies of index names by carrying out semantic word segmentation processing on the acquired index names and adopting a natural language processing model; screening dimension indexes and measurement indexes of each index vocabulary through a pre-constructed multi-dimension index table, and determining the atomic index codes of each dimension index and measurement index through an index dimension code mapping table; by sequencing and splicing preset rules, index codes with unique sequencing sequences are obtained, ambiguity generated by sequencing of different atomic index codes is avoided, the index codes are used for representing corresponding index names, and the standardization degree of a business index management architecture is increased.
Referring to fig. 2, a second embodiment of the method for generating index codes in an embodiment of the present invention includes:
201. acquiring historical service information, and carrying out abstract processing on the historical service information to obtain a plurality of characteristic words;
202. clustering the feature words by adopting a preset clustering model to obtain a plurality of dimension indexes with different dimensions and one or more measurement indexes;
In this embodiment, the abstract processing of the history service information specifically includes the following steps:
performing word segmentation processing on historical service information to obtain a plurality of segmented words and cleaning the segmented words to obtain a plurality of characteristic words, wherein the word segmentation cleaning comprises the steps of (1) constructing a stop word list and removing segmented words in the stop word list, wherein words which are commonly used and have no practical meaning, such as a mood assisted word, are recorded in the list: o, mo, yita, etc.; (2) Rare word removal, removal of too long or too short of a word segmentation, a well-known brand name, noisy characters, etc.;
each Word is then converted into a Word vector using a conventional model, such as one-hot (one-bit efficient coding), BOW (Bag of Words, bag of Words model), continuous Bag of Words model (Continuity-BOW, CBOW), skip-Gram model, word2vec model, etc., wherein for example, for the BOW Bag of Words model, we need to convert it into a three-dimensional TF-IDF (term frequency-inverse document frequency) matrix when converting it into a Word vector value, the three-dimensional TF-IDF can be regarded as a primary weighting for extracting text features;
performing data dimension reduction processing on the three-dimensional TF-IDF matrix by adopting PCA (Principal Component Analysis) and principal component analysis technology until the transformed data has the maximum variance, so as to obtain the dimension-reduced three-dimensional TF-IDF matrix, wherein each word in the TF-IDF matrix can be used as a dimension index or a measurement index after clustering processing of each characteristic word, and the dimension indexes or measurement indexes of different dimensions can be classified according to different clustering rules and corresponding storage partitions are defined.
203. Fixing the one or more measurement indexes, and combining the dimension indexes based on the affiliated dimension of the dimension indexes to obtain a corresponding multi-dimension index table;
in this embodiment, the multi-dimensional index table may be represented as a three-dimensional coordinate system, and a dimension layer represents a coordinate axis, and a cross section of an X axis, a Y axis, and a Z axis may be taken as a dimension class; dividing the partition equally according to the number of dimension categories and the dimension hierarchy level by taking an equal value on the cross section, namely taking the partition as a dimension member (dimension index) of the corresponding dimension category; one or more metrics defined in advance are fixed based on the intersection regions of the members of the different dimensions.
For equivalent equal division partitions, if the dimension hierarchy level in the time dimension is defined as year and quarter, each equal division partition is quarter, and one year comprises four partition intervals; for the number of dimension types, if there is an intersection between the time dimension and the product dimension, and the sales channel dimension, the fixed metric is the sales amount, then the intersection may be denoted as "sales amount of the first quarter a product B sales channel".
204. Coding the dimension index and the measurement index to obtain a corresponding atomic index code, and creating an index dimension code mapping table based on the atomic index code;
In this embodiment, the dimension indexes or the measurement indexes of different dimensions are encoded according to a predefined encoding rule, and written into the index dimension mapping table according to the dimension category sequence.
205. Acquiring index names of service demands;
206. performing semantic word segmentation on the index names by adopting a preset natural language processing model to obtain a plurality of index words;
207. acquiring a multi-dimensional index table and an index dimension coding mapping table, acquiring the multi-dimensional index table and the index dimension coding mapping table, and screening dimension indexes and measurement indexes corresponding to each index vocabulary from the multi-dimensional index table;
208. searching the dimension indexes and the atomic index codes corresponding to the measurement indexes from the index dimension code mapping table, and sequencing the atomic index codes according to a preset rule;
209. and splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index code of the demand index name.
In the embodiment of the invention, the construction process of the dimension index table and the coding mapping table is described in detail, the dimension index and the measurement index of different dimensions are obtained by carrying out clustering treatment on a plurality of characteristic words in the historical service information, the dimension index table and the measurement index are obtained by combining the dimension index table and the measurement index, then each dimension index and each measurement index are coded according to a preset coding rule and stored as the coding mapping table, and the method can be directly applied to the generation of the index codes in the later period, thereby improving the generation efficiency of the index codes.
Referring to fig. 3, a third embodiment of the method for generating an index code according to an embodiment of the present invention includes:
301. acquiring index names of service demands;
302. performing semantic word segmentation on the index names by adopting a preset natural language processing model to obtain a plurality of index words;
303. acquiring a multi-dimension index table and an index dimension coding mapping table;
304. extracting identification information of index types in the multi-dimensional index table, and determining a first type index and a second type index in the multi-dimensional index table based on the identification information;
in this embodiment, the multidimensional index table includes a dimension index and a measurement index, and the dimension index and the measurement index have different identification information, and the dimension index (first type index) and the measurement index (second type index) can be distinguished through the identification information;
305. matching the index vocabulary with the first type index, and determining one or more dimension indexes contained in the index vocabulary;
306. matching the screened index vocabulary with the second type index, and determining one or more measurement indexes contained in the index vocabulary;
through the measurement indexes in the multi-dimension index table, the measurement index vocabulary and the corresponding measurement indexes contained in the index vocabulary can be screened out; the dimension index vocabulary and the corresponding measurement index contained in the index vocabulary can be screened out through the dimension index in the multi-dimension index table, wherein the measurement index and the dimension index can be matched with the index vocabulary according to similar vocabulary, and the similar vocabulary comprises synonyms, homophones, error correction words and the like.
307. Judging whether the multidimensional index table contains dimension indexes and measurement indexes corresponding to all index vocabularies or not;
in this embodiment, the multidimensional index table may have dimension indexes corresponding to all index words, which may not be included in the multidimensional index table, because the multidimensional index table may not be updated or the index words may not be identified, so it is required to determine whether all index words match to the corresponding dimension indexes and measurement indexes.
308. If the index vocabulary is not contained, generating reminding information based on the index vocabulary not contained, so as to prompt a user to perfect the multi-dimensional index table.
In this embodiment, if there are dimension indexes or measurement indexes corresponding to index words that cannot be found in the multi-dimension index table, the user needs to manually maintain the multi-dimension index table, and newly adds dimension types and corresponding dimension indexes or measurement indexes in the multi-dimension index table.
309. Searching the dimension indexes and the atomic index codes corresponding to the measurement indexes from the index dimension code mapping table, and sequencing the atomic index codes according to a preset rule;
310. and splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index code of the demand index name.
In the embodiment of the invention, the method and the device for screening the dimension index and the measurement index corresponding to the index vocabulary from the multi-dimension index table are described in detail, and for the dimension index or the measurement index which is not contained in the multi-dimension index table, a user is required to re-develop the bottom technology according to the new index vocabulary requirement, so that the multi-dimension index table is perfected, and the standardization and the comprehensiveness of the multi-dimension index table are considered.
Referring to fig. 4, a fourth embodiment of the method for generating an index code according to the present invention includes:
401. acquiring index names of service demands;
402. determining the measurement caliber of the index name, and judging whether the measurement caliber of the index name meets the preset measurement caliber specification;
in this embodiment, the metric caliber refers to whether the words in the index names are normal or not, and whether the metric indexes are recorded in the multi-dimensional index table or not, for example, each metric index or dimension index in the index names has a wrong word, a synonym appears, and the metric index expression is different from the metric index record in the multi-dimensional index table, for example, the metric index expression in the index names is "first quarter and second quarter", so that the record content of the metric index in the multi-dimensional index table can be determined to be "first quarter and second quarter".
403. If yes, carrying out vocabulary entity standardization processing on the index names by adopting a preset character recognition library so as to accord with word segmentation processing rules of a preset natural language processing model.
In this embodiment, a plurality of data texts in the business field are acquired, including documents, journals, news manuscripts, blogs, web pages, and the like; extracting entity meanings of words and phrases in each data text; according to the entity meaning of each word and word in the index name, associating the corresponding single word and word, and storing the single word and word in a word recognition library; and then, according to each single word and each word in the index names, replacing the words and the characters corresponding to each index vocabulary in the multi-dimensional index table based on the word recognition library.
404. Performing semantic word segmentation on the index names by adopting a preset natural language processing model to obtain a plurality of index words;
405. acquiring a multi-dimensional index table and an index dimension coding mapping table, acquiring the multi-dimensional index table and the index dimension coding mapping table, and screening dimension indexes and measurement indexes corresponding to each index vocabulary from the multi-dimensional index table;
406. searching the dimension indexes and the atomic index codes corresponding to the measurement indexes from the index dimension code mapping table, and sequencing the atomic index codes according to a preset rule;
407. And splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index code of the demand index name.
In the embodiment of the invention, after the index name is acquired, whether the index replicates the preset measurement caliber is determined, and the index name is subjected to standardized processing so as to adapt to the word segmentation processing rule of the preset natural language model, thereby improving the efficiency of each subsequent index name processing.
The method for generating the index code in the embodiment of the present invention is described above, and the apparatus for generating the index code in the embodiment of the present invention is described below, referring to fig. 5, where an embodiment of the apparatus for generating the index code in the embodiment of the present invention includes:
an obtaining module 501, configured to obtain an index name of a service requirement;
the word segmentation module 502 is configured to perform semantic word segmentation on the index name by using a preset natural language processing model to obtain a plurality of index vocabularies;
a screening module 503, configured to obtain a multidimensional index table and an index dimension code mapping table, and screen dimension indexes and measurement indexes corresponding to the index vocabularies from the multidimensional index table;
the searching module 504 is configured to search the index dimension code mapping table for the atomic index codes corresponding to the dimension indexes and the measurement indexes, and order the atomic index codes according to a preset rule;
And the splicing module 505 is configured to splice the atomic index codes based on the sorting order of the atomic index codes, so as to obtain the index code of the requirement index name.
The embodiment of the invention provides an index management method based on natural language processing. The invention extracts a plurality of index vocabularies of index names by carrying out semantic word segmentation processing on the acquired index names and adopting a natural language processing model; screening dimension indexes and measurement indexes of each index vocabulary through a pre-constructed multi-dimension index table, and determining the atomic index codes of each dimension index and measurement index through an index dimension code mapping table; by sequencing and splicing preset rules, index codes with unique sequencing sequences are obtained, ambiguity generated by sequencing of different atomic index codes is avoided, the index codes are used for representing corresponding index names, and the standardization degree of a business index management architecture is increased.
Referring to fig. 6, another embodiment of the index code generating device in the embodiment of the present invention includes:
an obtaining module 501, configured to obtain an index name of a service requirement;
the word segmentation module 502 is configured to perform semantic word segmentation on the index name by using a preset natural language processing model to obtain a plurality of index vocabularies;
A screening module 503, configured to obtain a multidimensional index table and an index dimension code mapping table, and screen dimension indexes and measurement indexes corresponding to the index vocabularies from the multidimensional index table;
the searching module 504 is configured to search the index dimension code mapping table for the atomic index codes corresponding to the dimension indexes and the measurement indexes, and order the atomic index codes according to a preset rule;
and the splicing module 505 is configured to splice the atomic index codes based on the sorting order of the atomic index codes, so as to obtain the index code of the requirement index name.
Specifically, the index code generating device further includes:
the abstract processing module 506 is configured to obtain historical service information, and perform abstract processing on the historical service information to obtain a plurality of feature vocabularies;
the clustering module 507 is configured to perform clustering processing on the feature vocabularies by using a preset clustering model, so as to obtain a plurality of dimension indexes with different dimensions and one or more measurement indexes;
the combination module 508 is configured to fix the one or more metrics, and combine the dimension indexes based on the dimension to which the dimension indexes belong to obtain a corresponding multidimensional index table;
The encoding module 509 is configured to encode the dimension index and the metric index to obtain a corresponding atomic index code, and create an index dimension code mapping table based on the atomic index code.
Specifically, the screening module includes:
an extracting unit 5031, configured to extract identification information of a type of an index in the multi-dimensional index table, and determine a first type index and a second type index in the multi-dimensional index table based on the identification information;
a first matching unit 5032, configured to match the index vocabulary with the first type of index, and determine one or more dimension indexes included in the index vocabulary;
and a second matching unit 5033, configured to match the filtered index vocabulary with the second type of index, and determine one or more metric indexes contained in the index vocabulary.
Specifically, the index code generating device further includes:
a first judging module 510, configured to judge whether the multidimensional index table includes dimension indexes and measurement indexes corresponding to all the index vocabularies;
the generating module 511 is configured to generate, if the multi-dimensional index table does not include the dimension indexes and the measurement indexes corresponding to all the index vocabularies, a reminder based on the index vocabularies that are not included, so as to prompt the user to perfect the multi-dimensional index table.
Specifically, the index code generating device further includes:
a second determining module 512, configured to determine a measurement caliber of the index name, and determine whether the measurement caliber of the index name meets a preset measurement caliber specification;
and the standardization processing module 513 is configured to perform vocabulary entity standardization processing on the index name by using a preset word recognition library if the measurement caliber of the index name meets a preset measurement caliber specification, so as to meet a word segmentation processing rule of a preset natural language processing model.
Specifically, the index code generating device further includes a report display module 514, configured to obtain, after obtaining index codes of all index names in the service requirement, a plurality of metric data corresponding to the service requirement based on the index codes; and generating a business report according to the measurement data and displaying the business report.
Specifically, the index code is also stored in the blockchain.
In the embodiment of the invention, the multi-dimension index table is obtained by clustering the characteristic words in the historical service information, and the code is encoded according to the preset rule to obtain the code mapping table, so that the method can be directly applied to the generation of the index codes in the later period, and the generation efficiency of the index codes is improved; the method comprises the steps of screening dimension indexes and measurement indexes corresponding to index words from a multi-dimension index table, perfecting the multi-dimension index table according to dimension indexes or measurement indexes which are not contained in the multi-dimension index table, and considering standardization and comprehensiveness of the multi-dimension index table; finally, after the index name is acquired, determining whether the index replicates the preset measurement caliber, and carrying out standardized processing on the index name so as to adapt to word segmentation processing rules of a preset natural language model, thereby improving the efficiency of each processing of the subsequent index name.
The index code generating device in the embodiment of the present invention is described in detail above in fig. 5 and 6 from the point of view of modularized functional entities, and the index code generating device in the embodiment of the present invention is described in detail below from the point of view of hardware processing.
Fig. 7 is a schematic structural diagram of an index code generating device according to an embodiment of the present invention, where the index code generating device 700 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 710 (e.g., one or more processors) and a memory 720, and one or more storage media 730 (e.g., one or more mass storage devices) storing application programs 733 or data 732. Wherein memory 720 and storage medium 730 may be transitory or persistent. The program stored in the storage medium 730 may include one or more modules (not shown), each of which may include a series of instruction operations in the index code generation device 700. Still further, the processor 710 may be configured to communicate with the storage medium 730 and execute a series of instruction operations in the storage medium 730 on the index code generation device 700.
The index code generation device 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input/output interfaces 760, and/or one or more operating systems 731, such as Windows Serve, mac OS X, unix, linux, freeBSD, etc. It will be appreciated by those skilled in the art that the index code generation device structure shown in fig. 7 is not limiting of the index code generation device and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.
The present invention also provides an index code generating device, including a memory and a processor, where the memory stores computer readable instructions that, when executed by the processor, cause the processor to execute the steps of the index code generating method in the above embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, or may be a volatile computer readable storage medium, in which instructions are stored which, when executed on a computer, cause the computer to perform the steps of the index code generation method.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. An index code generation method, characterized in that the index code generation method comprises:
Acquiring index names of service demands; before the index name of the service requirement is obtained, the method further comprises the following steps:
acquiring historical service information, and carrying out abstract processing on the historical service information to obtain a plurality of characteristic words;
clustering the feature words by adopting a preset clustering model to obtain dimension indexes of a plurality of different dimensions and one or more measurement indexes;
fixing the one or more measurement indexes, and combining the dimension indexes based on the affiliated dimension of the dimension indexes to obtain a corresponding multi-dimension index table;
coding the dimension index and the measurement index to obtain a corresponding atomic index code, and creating an index dimension code mapping table based on the atomic index code;
after the index name of the service requirement is obtained, the method further comprises the following steps:
determining the measurement caliber of the index name, and judging whether the measurement caliber of the index name meets the preset measurement caliber specification;
if yes, carrying out vocabulary entity standardization processing on the index names by adopting a preset character recognition library so as to accord with word segmentation processing rules of a preset natural language processing model;
Performing semantic word segmentation on the index names by adopting a preset natural language processing model to obtain a plurality of index words;
acquiring a multi-dimensional index table and an index dimension coding mapping table, and screening dimension indexes and measurement indexes corresponding to each index vocabulary from the multi-dimensional index table;
searching each dimension index and each atomic index code corresponding to each measurement index from the index dimension code mapping table, and sequencing each atomic index code according to a preset rule; the step of screening the dimension index and the measurement index corresponding to each index vocabulary from the multi-dimension index table comprises the following steps:
extracting identification information of index types in the multi-dimensional index table, and determining a first type index and a second type index in the multi-dimensional index table based on the identification information;
matching the index vocabulary with the first type index, and determining one or more dimension indexes contained in the index vocabulary;
matching the screened index vocabulary with the second type index, and determining one or more measurement indexes contained in the index vocabulary;
splicing the atomic index codes based on the sorting order of the atomic index codes to obtain index codes of the demand index names; after splicing the atomic index codes according to the sorting order of the atomic index codes to obtain the index code of the demand index name, the method further comprises the following steps:
Acquiring a plurality of measurement data corresponding to the service demand based on each index code after the index codes of all index names in the service demand are obtained;
and generating a business report according to each measurement data and displaying the business report.
2. The method of generating an index code according to claim 1, further comprising, before said selecting a dimension index and a metric index corresponding to each of said index words from said multi-dimensional index table:
judging whether the multidimensional index table contains dimension indexes and measurement indexes corresponding to all index vocabularies or not;
if the index vocabulary is not contained, generating reminding information based on the index vocabulary not contained, so as to prompt a user to perfect the multi-dimensional index table.
3. The index code generation method according to claim 1, wherein the index code is stored in a blockchain.
4. An index code generation device, characterized in that the index code generation device includes:
the acquisition module is used for acquiring index names of service demands; before the index name of the service requirement is obtained, the method further comprises the following steps:
acquiring historical service information, and carrying out abstract processing on the historical service information to obtain a plurality of characteristic words;
Clustering the feature words by adopting a preset clustering model to obtain dimension indexes of a plurality of different dimensions and one or more measurement indexes;
fixing the one or more measurement indexes, and combining the dimension indexes based on the affiliated dimension of the dimension indexes to obtain a corresponding multi-dimension index table;
coding the dimension index and the measurement index to obtain a corresponding atomic index code, and creating an index dimension code mapping table based on the atomic index code;
after the index name of the service requirement is obtained, the method further comprises the following steps:
determining the measurement caliber of the index name, and judging whether the measurement caliber of the index name meets the preset measurement caliber specification;
if yes, carrying out vocabulary entity standardization processing on the index names by adopting a preset character recognition library so as to accord with word segmentation processing rules of a preset natural language processing model;
the word segmentation module is used for carrying out semantic word segmentation on the index names by adopting a preset natural language processing model to obtain a plurality of index words;
the screening module is used for acquiring a multi-dimension index table and an index dimension coding mapping table, and screening dimension indexes and measurement indexes corresponding to each index vocabulary from the multi-dimension index table;
The searching module is used for searching the dimension indexes and the atomic index codes corresponding to the measurement indexes from the index dimension code mapping table, and sequencing the atomic index codes according to a preset rule; the step of screening the dimension index and the measurement index corresponding to each index vocabulary from the multi-dimension index table comprises the following steps:
extracting identification information of index types in the multi-dimensional index table, and determining a first type index and a second type index in the multi-dimensional index table based on the identification information;
matching the index vocabulary with the first type index, and determining one or more dimension indexes contained in the index vocabulary;
matching the screened index vocabulary with the second type index, and determining one or more measurement indexes contained in the index vocabulary;
the splicing module is used for splicing the atomic index codes based on the sorting order of the atomic index codes to obtain the index codes of the demand index names; after splicing the atomic index codes according to the sorting order of the atomic index codes to obtain the index code of the demand index name, the method further comprises the following steps:
Acquiring a plurality of measurement data corresponding to the service demand based on each index code after the index codes of all index names in the service demand are obtained;
and generating a business report according to each measurement data and displaying the business report.
5. An index code generation device, characterized in that the index code generation device comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the index code generation apparatus to perform the index code generation method of any one of claims 1-3.
6. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the index code generation method according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011298686.9A CN112364603B (en) | 2020-11-19 | 2020-11-19 | Index code generation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011298686.9A CN112364603B (en) | 2020-11-19 | 2020-11-19 | Index code generation method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112364603A CN112364603A (en) | 2021-02-12 |
| CN112364603B true CN112364603B (en) | 2023-10-03 |
Family
ID=74532961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011298686.9A Active CN112364603B (en) | 2020-11-19 | 2020-11-19 | Index code generation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112364603B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113609159A (en) * | 2021-08-09 | 2021-11-05 | 北京金山云网络技术有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN113590607A (en) * | 2021-09-29 | 2021-11-02 | 国网江苏省电力有限公司营销服务中心 | Electric power marketing report realization method and system based on report factor |
| CN114416850A (en) * | 2022-01-26 | 2022-04-29 | 平安科技（深圳）有限公司 | Multi-dimensional data processing method and device, electronic equipment and storage medium |
| CN115150201B (en) * | 2022-09-02 | 2022-11-08 | 南通市艺龙科技有限公司 | Remote encryption transmission method for cloud computing data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038175A (en) * | 2017-09-30 | 2018-05-15 | 用友金融信息技术股份有限公司 | Multidimensional data dynamically associates querying method, device, computer equipment and medium |
| CN110427434A (en) * | 2019-06-28 | 2019-11-08 | 苏宁云计算有限公司 | A kind of multidimensional data query method and device |
| CN111125121A (en) * | 2020-03-30 | 2020-05-08 | 四川新网银行股份有限公司 | Real-time data display method based on HBase table |
| CN111737476A (en) * | 2020-08-05 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Text processing method and device, computer readable storage medium and electronic equipment |
| CN111949655A (en) * | 2020-07-24 | 2020-11-17 | 北京每日优鲜电子商务有限公司 | Form display method and device, electronic equipment and medium |
-
2020
- 2020-11-19 CN CN202011298686.9A patent/CN112364603B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038175A (en) * | 2017-09-30 | 2018-05-15 | 用友金融信息技术股份有限公司 | Multidimensional data dynamically associates querying method, device, computer equipment and medium |
| CN110427434A (en) * | 2019-06-28 | 2019-11-08 | 苏宁云计算有限公司 | A kind of multidimensional data query method and device |
| CN111125121A (en) * | 2020-03-30 | 2020-05-08 | 四川新网银行股份有限公司 | Real-time data display method based on HBase table |
| CN111949655A (en) * | 2020-07-24 | 2020-11-17 | 北京每日优鲜电子商务有限公司 | Form display method and device, electronic equipment and medium |
| CN111737476A (en) * | 2020-08-05 | 2020-10-02 | 腾讯科技（深圳）有限公司 | Text processing method and device, computer readable storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112364603A (en) | 2021-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112364603B (en) | Index code generation method, device, equipment and storage medium | |
| US9195639B2 (en) | Computer-based system and method for generating, classifying, searching, and analyzing standardized text templates and deviations from standardized text templates | |
| CN110162754B (en) | Method and equipment for generating post description document | |
| CN111986792B (en) | Medical institution scoring method, device, equipment and storage medium | |
| JP7208872B2 (en) | Systems and methods for generating proposals based on request for proposals (RFPs) | |
| Li et al. | A policy-based process mining framework: mining business policy texts for discovering process models | |
| CN113283675B (en) | Index data analysis method, device, equipment and storage medium | |
| US9558182B1 (en) | Smart terminology marker system for a language translation system | |
| CN112632289B (en) | Processing method, device, equipment and storage medium of business clause data | |
| CN111209411A (en) | Document analysis method and device | |
| CN111259160A (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN112631889B (en) | Portrayal method, device, equipment and readable storage medium for application system | |
| CN113159118A (en) | Logistics data index processing method, device, equipment and storage medium | |
| CN114692628A (en) | Sample generation method, model training method, text extraction method and text extraction device | |
| CN116897347A (en) | System and method for parsing administrative documents and other documents for machine scoring | |
| Friedrich | Complexity and entropy in legal language | |
| Santamarina et al. | How to code a million missions: Developing bespoke nonprofit activity codes using machine learning algorithms | |
| Howard | Phonetic spelling algorithm implementations for R | |
| CN113269179A (en) | Data processing method, device, equipment and storage medium | |
| CN116244421A (en) | Method, device, equipment and readable storage medium for matching project names | |
| CN113571198B (en) | Conversion rate prediction method, conversion rate prediction device, conversion rate prediction equipment and storage medium | |
| CN113240325B (en) | Data processing method, device, equipment and storage medium | |
| CN114926082A (en) | Artificial intelligence-based data fluctuation early warning method and related equipment | |
| CN112818215A (en) | Product data processing method, device, equipment and storage medium | |
| CN110909112B (en) | Data extraction method, device, terminal equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |