CN117435817B - BI intelligent center system based on industry big data - Google Patents
BI intelligent center system based on industry big data Download PDFInfo
- Publication number
- CN117435817B CN117435817B CN202311753110.0A CN202311753110A CN117435817B CN 117435817 B CN117435817 B CN 117435817B CN 202311753110 A CN202311753110 A CN 202311753110A CN 117435817 B CN117435817 B CN 117435817B
- Authority
- CN
- China
- Prior art keywords
- data
- features
- sales
- value
- layer
- 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
- 238000000034 method Methods 0.000 claims abstract description 80
- 239000010410 layer Substances 0.000 claims description 141
- 238000004519 manufacturing process Methods 0.000 claims description 67
- 230000001133 acceleration Effects 0.000 claims description 19
- 235000015097 nutrients Nutrition 0.000 claims description 19
- 239000002356 single layer Substances 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 5
- 238000003306 harvesting Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000012797 qualification Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/2163—Partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing, and discloses a BI intelligent center system based on industrial big data; constructing multi-level data rings by BI industry data, dividing the multi-level data rings into latent features and target features, matching the request features with the target features in a request feature list one by one, generating recommended instructions based on matching results, and formulating a hierarchical control scheme according to the recommended instructions to inquire the data in the data rings; compared with the prior art, the method and the device can generate the relevancy recommendation instruction matched with the request feature, accurately recommend the BI industry data meeting the requirements in the data ring in a small range, avoid recommending a large amount of irrelevant data, shorten the query time of a user on the heart meter data, and simultaneously recommend the BI industry data with different relevancy according to the requirements of the user to realize flexible switching of relevancy among the BI industry data, thereby helping the user to quickly and accurately make excellent decisions for enterprise development.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a BI intelligent center system based on industrial big data.
Background
Traditional business intelligence (Business Intelligence, abbreviated as BI) systems mainly focus on analysis and decision support of enterprise internal data, but with rapid development of the Internet and the Internet of things, the scale and complexity of industrial big data are continuously increased, and the traditional BI systems cannot meet the requirements of comprehensive analysis and utilization of the industrial big data.
The Chinese patent with the application publication number of CN115730973A discloses a BI method through big data and intelligent management, which adopts a dynamic analysis model, so that each user can completely remove the data and display fields according to the application scene and the requirements of the user and can save the data and the display fields as a scheme, thereby enabling all data association in the method to be smooth and unobstructed, and further improving the efficiency in operation;
the prior art has the following defects:
when the existing BI intelligent center system realizes user data query operation, all data associated with the features are simultaneously recommended according to the containing features of the user request data, so that the data volume for the user to query and browse is large, the required data with high matching degree cannot be quickly and accurately queried, and meanwhile, the recommended massive data are different in association degree, so that the associated data cannot be accurately selected preferentially, and further, the user cannot provide accurate and reasonable decisions for enterprises.
In view of the above, the present invention proposes a BI intelligent center system based on industrial big data to solve the above-mentioned problems.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the following technical scheme for achieving the purposes: an intelligent BI center system based on industrial big data is applied to intelligent server, and the system includes:
the industry data acquisition module acquires BI industry data of a selected enterprise;
the data ring construction module is used for constructing a multi-level data ring based on BI industrial data;
the target feature dividing module marks basic features of each layer in the data ring and divides the basic features into latent features and target features;
the request feature identification module marks request features in the request data of the user and generates a request feature list based on the request features;
the feature matching module is used for matching the request features in the request feature list with the target features one by one and generating a recommendation instruction based on a matching result;
and the control query module is used for formulating a hierarchical control scheme according to the recommended instruction and querying the target features in the data ring based on the hierarchical control scheme.
Further, the BI industry data includes qualified production values, effective sales values, and revenue acceleration;
the method for acquiring the qualified production value comprises the following steps:
randomly selecting past enterprisesCounting periods, marking a period starting point and a period ending point, wherein the period starting point and the period ending point of any one counting period do not coincide with the period ending point of the previous counting period and the period starting point of the next counting period;
acquisition through industry big databaseCounting the total quantity of products and the quantity of qualified products in a period;
will beTotal amount of individual products>After the number of the qualified products is compared, the +.>Sub-qualification values;
the expression of the sub-fit value is:
;
in the method, in the process of the invention,is->Sub-fit values for a statistical period, +.>Is->Number of good for each counting period, +.>Is->Counting the total amount of the products in a period;
at the position ofIn the sub-fit values, selecting +.>Sub-fit value, < ->Less than->And will->The sub-qualified values are accumulated and averaged to obtain qualified production values;
the expression of the qualified production value is:
;
in the method, in the process of the invention,for qualified production value, < >>Is->Sub-fit values.
Further, the method for acquiring the effective sales value comprises the following steps:
acquisition through industry big databaseThe product volume and the product return volume of each sales area in the same sales period;
according toIndividual product volume sum->The product quantity is->A pre-sales value;
the expression for the pre-sales value is:
:
in the method, in the process of the invention,is->Pre-sales value of individual sales area, +.>Is->Product volume in sales area, +.>Is->Product returns for each sales area;
removing the maximum value and the minimum value of the pre-sales valueAccumulating the pre-sales values and then averaging to obtain an effective sales value;
the expression for the effective sales value is:
;
in the method, in the process of the invention,for effective sales value, ++>Is->A pre-sales value.
Further, the acquisition method of the revenue increasing speed comprises the following steps:
acquiring past through enterprise financial statementA monthly sales amount and a monthly payout amount;
will beSales amount and->After comparison of the individual expenditure amounts, a +.>A monthly revenue amount;
the expression of the moon balance is:
;
in the method, in the process of the invention,is->The amount of nutrient receipts in one month->Is->Sales amount for month->Is the firstA monthly payout amount;
removing the month credit amount lower than the preset credit threshold value to obtainAn effective nutrient amount->Less than or equal to;
Will beThe effective revenue amounts are accumulated and averaged to obtain the revenue acceleration;
the expression of the nutrient harvest acceleration is:
;
in the method, in the process of the invention,for increasing nutrient and nutrient, add->Is->And an effective credit amount.
Further, the method for constructing the data ring comprises the following steps:
constructing blank inner layers, middle layers and outer layers, wherein the inner layers are positioned at the inner sides of the middle layers, and the outer layers are positioned at the outer sides of the middle layers;
respectively establishing a data association channel among the inner layer, the middle layer and the outer layer;
respectively setting a controllable cut-off point at two ends of the data association channel;
and respectively importing the qualified production value, the effective sales value and the revenue increasing speed into the inner layer, the middle layer and the outer layer to construct a multi-level data ring.
Further, the method for dividing the latent feature and the target feature comprises the following steps:
marking the total quantity of products, the quantity of qualified products, the sub-qualified value and the qualified production value in the inner layer of the data ring, and marking the total quantity of the products, the quantity of the sub-qualified values and the qualified production value as basic characteristics of the inner layer;
dividing the total quantity of products, the quantity of qualified products and the sub-qualified value into latent features of an inner layer, and dividing the qualified production value into target features of the inner layer;
marking the product volume, the product withdrawal volume, the pre-sales value and the effective sales value in the middle layer of the data ring as the basic characteristics of the middle layer;
dividing the product volume, the product withdrawal volume and the pre-sales value into middle-layer latent features, and dividing the effective sales value into middle-layer target features;
marking the month sales amount, the month expenditure amount, the month income amount and the income acceleration rate on the outer layer of the data ring, and recording the month sales amount, the month expenditure amount, the month income amount and the income acceleration rate as basic characteristics of the outer layer;
the monthly sales amount, the monthly expenditure amount and the monthly revenue amount are divided into the latency characteristics of the outer layer, and the revenue increasing speed is divided into the target characteristics of the outer layer.
Further, the request features include a qualified production feature, an effective sales feature, and an revenue feature;
the marking method of the qualified production characteristics, the effective sales characteristics and the revenue characteristics comprises the following steps:
traversing all feature phrases in the request data from the starting point of the request data;
marking the character phrase containing the word of 'qualified production' as the qualified production character;
marking the characteristic phrase containing the word of effective sales as effective sales characteristic;
the characteristic phrase containing the "nutrient" word is marked as nutrient characteristic.
Further, the method for generating the request feature list comprises the following steps:
sequentially numbering the involution production features, the effective sales features and the revenue features according to the sequence of the request feature marks;
and (3) arranging the numbers respectively belonging to the qualified production characteristics, the effective sales characteristics and the revenue characteristics in ascending order to generate a request characteristic list.
Further, the recommendation instructions comprise a single-layer recommendation instruction, a double-layer recommendation instruction and a full-layer recommendation instruction;
the recommendation method of the single-layer recommendation instruction, the double-layer recommendation instruction and the full-layer recommendation instruction comprises the following steps:
counting the occurrence times of qualified production features, effective sales features and revenue features in the feature phrase respectively;
comparing the occurrence times of the qualified production features, the effective sales features and the revenue features with the qualified production values, the effective sales values and the revenue accelerating storage amounts one by one respectively to obtain matching coincidence degrees;
comparing the matching coincidence degree with a preset first coincidence threshold value and a second coincidence threshold value, wherein the first coincidence threshold value is smaller than the second coincidence threshold value;
when the matching coincidence degree is smaller than a first coincidence threshold value, generating a single-layer recommendation instruction;
when the first coincidence threshold value is smaller than or equal to the matching coincidence degree and the matching coincidence degree is smaller than the second coincidence threshold value, generating a double-layer recommendation instruction;
and when the matching overlap ratio is greater than or equal to a second overlap threshold, generating a full-layer recommended instruction.
Further, the hierarchical control scheme comprises a scheme for controlling the breakpoints at two ends of two data-associated channels to be conducted, a scheme for controlling the breakpoints at two ends of one data-associated channel to be conducted, and a scheme for controlling the breakpoints at two ends of two data-associated channels to be disconnected;
the method for making the scheme for controlling the breakpoints at two ends of two data-associated channels to be conducted uniformly and the scheme for controlling the breakpoints at two ends of one data-associated channel to be conducted uniformly comprises the following steps:
when the recommended instruction is a single-layer recommended instruction, a scheme for controlling the disconnection of controllable interception points at two ends of the two data association channels is formulated;
when the recommended instruction is a double-layer recommended instruction, a controllable cutoff point conduction scheme for controlling two ends of a data association channel is formulated;
when the recommended instruction is a full-layer recommended instruction, a controllable cutting-off point all-on scheme for controlling two ends of the two data association channels is formulated.
The technical effect and the advantages of the BI intelligent center system based on the industrial big data are as follows:
the method comprises the steps of constructing a multi-level data ring by collecting BI industry data of a selected enterprise, marking basic characteristics of each level in the data ring, dividing the basic characteristics into latent characteristics and target characteristics, marking request characteristics in request data of a user, generating a request characteristic list, then matching the request characteristics in the request characteristic list with the target characteristics one by one, generating a recommended instruction based on a matching result, formulating a level control scheme according to the recommended instruction, and inquiring the target characteristics in the data ring based on the level control scheme to obtain required data; compared with the prior art, the BI industry data can be accurately identified, and after the request features of the user are matched with the target features, the relevancy recommendation instruction matched with the request features is generated, so that the BI industry data meeting the requirements in the data ring is accurately recommended in a small range, the recommendation of a large amount of irrelevant data is avoided, the query time of the user on the heart meter data is shortened, meanwhile, the BI industry data with different relevancy can be recommended according to the requirements of the user, the flexible switching of the relevancy between the BI industry data is realized, and the user is helped to quickly and accurately make excellent decisions for the enterprise development.
Drawings
FIG. 1 is a schematic diagram of a BI intelligent center system based on industrial big data according to embodiment 1 of the present invention;
FIG. 2 is a schematic flow chart of a BI intelligent center method based on industrial big data provided in embodiment 2 of the present invention;
FIG. 3 is a schematic diagram of a data ring according to embodiment 1 of the present invention;
fig. 4 is a schematic diagram of a structural schematic diagram of an electronic device according to embodiment 3 of the present invention;
fig. 5 is a schematic structural diagram of a computer readable storage medium according to embodiment 4 of 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.
Example 1: referring to fig. 1, the BI intelligent center system based on industrial big data in this embodiment is applied to an intelligent server, and the system includes:
the industry data acquisition module acquires BI industry data of a selected enterprise;
the BI industry data refers to comprehensive data related to industry and products generated by enterprises in production, management and sales activities, and data support can be provided for analysis of past production, management and sales conditions of the enterprises by collecting the BI industry data;
the BI industry data comprises qualified production values, effective sales values and revenue acceleration;
the qualified production value refers to the ratio amplitude of the quantity of qualified products which are produced and inspected by the enterprises in the production and manufacturing activities in the total quantity of the products, and when the qualified production value is larger, the quantity of qualified products which are inspected and inspected by the enterprises is larger;
the method for acquiring the qualified production value comprises the following steps:
randomly selected rabbetPast and pastCounting periods, marking a period starting point and a period ending point, wherein the period starting point and the period ending point of any one counting period do not coincide with the period ending point of the previous counting period and the period starting point of the next counting period; the statistical period refers to a time interval for an enterprise to judge and count qualified data of a product in the production and manufacturing process, the duration of the statistical period can be set by the enterprise according to the actual different production and manufacturing conditions and can also be set according to the preset duration, and when the statistical period is set according to the preset duration, one statistical period corresponds to 24 hours; meanwhile, the end point of the previous cycle does not coincide with the start point of the next cycle, the +.>The statistical periods are independently opened so that +.>The phenomenon of correlation of the product quality data before and after each statistical period can not occur, thereby ensuring +.>The relative independence of the product quality data in the individual statistical periods;
acquisition through industry big databaseCounting the total quantity of products and the quantity of qualified products in a period;
will beTotal amount of individual products>After the number of the qualified products is compared, the +.>Sub-qualification values;
the expression of the sub-fit value is:
;
in the method, in the process of the invention,is->Sub-fit values for a statistical period, +.>Is->Number of good for each counting period, +.>Is->Counting the total amount of the products in a period;
at the position ofIn the sub-fit values, selecting +.>Sub-fit value, < ->Less than->And will->The sub-qualified values are accumulated and averaged to obtain qualified production values; the data can be randomly selected again by the interval selection mode, so that the phenomenon that a plurality of adjacent statistical periods are all influenced by association caused by serious product quality accidents of enterprises is further avoided;
the expression of the qualified production value is:
;
in the method, in the process of the invention,for qualified production value, < >>Is->Sub-fit values.
The effective sales value refers to the ratio relation between the number of products successfully sold and the number of products planned to be sold by an enterprise in sales activities, and the performance of the products of the enterprise in the sales process can be clearly and intuitively known by collecting the effective sales value;
the method for acquiring the effective sales value comprises the following steps:
acquisition through industry big databaseThe product volume and the product return volume of each sales area in the same sales period; the sales cycle refers to a time interval for an enterprise to count the sales amount of a product in a specific time period in the sales process, the sales cycle is generally set by the enterprise according to the supply and demand relationship of the market, when the supply and demand in the market are greater than those in the market, the sales cycle is longer, when the supply and demand in the market are less than those in the market, the sales cycle is shorter, and an exemplary one sales cycle is 72 hours;
according toIndividual product volume sum->The product quantity is->A pre-sales value;
the expression for the pre-sales value is:
:
in the method, in the process of the invention,is->Pre-sales value of individual sales area, +.>Is->Product volume in sales area, +.>Is->Product returns for each sales area;
removing the maximum value and the minimum value of the pre-sales valueAccumulating the pre-sales values and then averaging to obtain an effective sales value;
the expression for the effective sales value is:
;
in the method, in the process of the invention,for effective sales value, ++>Is->A pre-sales value.
The revenue acceleration refers to the increase of the enterprise income in unit time in the marketing and sales activities of enterprise products, and the business expense condition of the enterprise in the past time period can be accurately known by collecting the revenue acceleration, so that the past and current financial conditions of the enterprise can be judged;
the acquisition method for the revenue acceleration comprises the following steps:
acquiring past through enterprise financial statementA monthly sales amount and a monthly payout amount;
will beSales amount and->After comparison of the individual expenditure amounts, a +.>A monthly revenue amount;
the expression of the moon balance is:
;
in the method, in the process of the invention,is->The amount of nutrient receipts in one month->Is->Sales amount for month->Is the firstA monthly payout amount;
removing the month credit amount lower than the preset credit threshold value to obtainAn effective nutrient amount->Less than or equal toThe method comprises the steps of carrying out a first treatment on the surface of the The preset revenue threshold value is an amount value for judging that enterprise revenue reaches the minimum standard, and only when the enterprise monthly revenue amount reaches or is higher than the minimum standard amount value, the enterprise can be indicated that effective revenue amount exists in the month, so that data with lower monthly revenue amount can be effectively eliminated, the calculated amount of the data can be reduced, and useless interference data can be eliminated;
will beThe effective revenue amounts are accumulated and averaged to obtain the revenue acceleration;
the expression of the nutrient harvest acceleration is:
;
in the method, in the process of the invention,for increasing nutrient and nutrient, add->Is->And an effective credit amount.
The data ring construction module is used for constructing a multi-level data ring based on BI industrial data;
the data ring is a set for providing all types of data support for all levels of decision making processes of enterprises, the multi-level data ring is a data set with a plurality of package layers, each package layer stores different types of BI industrial data, and each package layer refers to different BI industrial data;
because the types of data contained in the BI industry data are different, in order to relatively and independently collect all types of data in the BI industry data, a multi-level data ring needs to be constructed;
the construction method of the data ring comprises the following steps:
constructing blank inner layers, middle layers and outer layers, wherein the inner layers are positioned at the inner sides of the middle layers, and the outer layers are positioned at the outer sides of the middle layers;
respectively establishing a data association channel among the inner layer, the middle layer and the outer layer; the data association channel is a channel capable of carrying out bidirectional transmission on data contained in the inner layer, the middle layer and the outer layer, and the data among the inner layer, the middle layer and the outer layer can have certain association on the basis of keeping relative independence through the transmission of the data association channel;
respectively setting a controllable cut-off point at two ends of the data association channel; the controllable cut-off points are used for respectively controlling the opening and closing of the data association channels at two ends of the data association channels, so that the association of the data contained in the inner layer, the middle layer and the outer layer is controlled to be on-off, and the independent and association control effects of the data are realized;
respectively importing a qualified production value, an effective sales value and a revenue increasing speed into an inner layer, a middle layer and an outer layer to construct a multi-level data ring;
referring to fig. 3, the above method for constructing a data ring is actually applied to obtain a structure diagram of the data ring, where C1, C2, and C3 are an inner layer, a middle layer, and an outer layer respectively, TD is a data association channel, and JDD is a controllable cut-off point;
the target feature dividing module marks basic features of each layer in the data ring and divides the basic features into latent features and target features;
the target features are basic features corresponding to BI industry data which can be directly queried and browsed in the current state of the data ring, and the types of the BI industry data contained in each layer of the data ring are inconsistent, so that the first target features of each layer of the data ring are inconsistent, and the data contained in each layer of the data ring can be rapidly identified and confirmed by marking the first target features, thereby providing convenience for querying and browsing of the subsequent BI industry data; the latent features are basic features corresponding to BI industry data which cannot be directly queried and browsed in the current state in the data ring, and the latent features corresponding to the target features can be queried and browsed only by querying and browsing the target features;
the basic features are features shared by the corresponding BI industry data in each layer in the data ring, the data condition of each layer in the data ring can be comprehensively and generally summarized through the basic features, and in order to obtain specific types of data more accurately, target features need to be distinguished from the basic features;
the method for dividing the latent feature and the target feature comprises the following steps:
marking the total quantity of products, the quantity of qualified products, the sub-qualified value and the qualified production value in the inner layer of the data ring, and marking the total quantity of the products, the quantity of the sub-qualified values and the qualified production value as basic characteristics of the inner layer;
dividing the total quantity of products, the quantity of qualified products and the sub-qualified value into latent features of an inner layer, and dividing the qualified production value into target features of the inner layer;
marking the product volume, the product withdrawal volume, the pre-sales value and the effective sales value in the middle layer of the data ring as the basic characteristics of the middle layer;
dividing the product volume, the product withdrawal volume and the pre-sales value into middle-layer latent features, and dividing the effective sales value into middle-layer target features;
marking the month sales amount, the month expenditure amount, the month income amount and the income acceleration rate on the outer layer of the data ring, and recording the month sales amount, the month expenditure amount, the month income amount and the income acceleration rate as basic characteristics of the outer layer;
dividing the month sales amount, the month expenditure amount and the month harvest amount into latent features of the outer layer, and dividing the harvest acceleration into target features of the outer layer;
the request feature identification module marks request features in the request data of the user and generates a request feature list based on the request features;
when a user needs to inquire and browse BI industrial data in a data ring, the user needs to input inquiry and browse request data into the data ring, and as the request data contains more characteristics, the request data cannot accurately correspond to target characteristics of each level in the data ring at the first time, and the request characteristics in the request data need to be identified, so that the request processing time of the user request data is shortened, and the inquiry rate is improved;
the request features are representative features in the request data, the ratio of the request features in the request data is the largest, and the request features can be as close to the real intention of the user in the request data as possible;
the request features comprise qualified production features, effective sales features and revenue features, and the marking method of the qualified production features, the effective sales features and the revenue features comprises the following steps:
traversing all feature phrases in the request data from the starting point of the request data; the characteristic phrase refers to phrases containing characteristic word patterns such as ' qualified production ', ' effective sales ', ' revenue ', and the like, and each characteristic phrase contains at least one word pattern of ' qualified production ', ' effective sales ', ' revenue ', ' the like;
marking the character phrase containing the word of 'qualified production' as the qualified production character;
marking the characteristic phrase containing the word of effective sales as effective sales characteristic;
marking the characteristic phrase containing the 'camp' word as camp characteristic;
the method for generating the request feature list comprises the following steps:
sequentially numbering the involution production features, the effective sales features and the revenue features according to the sequence of the request feature marks;
the numbers belonging to the qualified production features, the effective sales features and the revenue features are arranged in ascending order to generate a request feature list;
by way of example, the method for generating the request feature list is actually applied to obtain the request feature list, as shown in table 1:
table 1: request feature arrangement table
The feature matching module is used for matching the request features in the request feature list with the target features one by one and generating a recommendation instruction based on a matching result;
the recommended instruction is an instruction for making association degree with successfully matched request features after the request features are matched with target features, and because BI industry data in the data ring is updated and iterated along with continuous accumulation of enterprise data, association degree between BI industry data in each level of the data ring is continuously developed and changed, and different recommended instructions are needed to be made for different association degrees according to the matching result of the request features and the target features;
the recommendation instructions comprise a single-layer recommendation instruction, a double-layer recommendation instruction and a full-layer recommendation instruction; the recommendation method of the single-layer recommendation instruction, the double-layer recommendation instruction and the full-layer recommendation instruction comprises the following steps:
counting the occurrence times of qualified production features, effective sales features and revenue features in the feature phrase respectively;
comparing the occurrence times of the qualified production features, the effective sales features and the revenue features with the qualified production values, the effective sales values and the revenue accelerating storage amounts one by one respectively to obtain matching coincidence degrees;
comparing the matching coincidence degree with a preset first coincidence threshold value and a second coincidence threshold value, wherein the first coincidence threshold value is smaller than the second coincidence threshold value; the preset first overlapping threshold value and the second overlapping threshold value are used for judging the association degree between BI industry data contained in each level in the data ring, when the matching overlapping degree is larger, the association degree between the request feature and the target feature is shown to be stronger, the association degree between the BI industry data of each level in the data ring is stronger, and the preset first overlapping threshold value and the second overlapping threshold value are obtained through coefficient optimization after acquiring matching overlapping degree values corresponding to association degree intensity of the BI industry data in a large number of historical data rings;
when the matching coincidence degree is smaller than a first coincidence threshold value, the fact that the correlation between BI industry data of each level in the data ring is weak is indicated, and a single-layer recommendation instruction is generated;
when the first coincidence threshold value is smaller than or equal to the matching coincidence degree and the matching coincidence degree is smaller than the second coincidence threshold value, the relevance among the BI industry data of each level in the data ring is described, and a double-layer recommendation instruction is generated;
when the matching overlap ratio is greater than or equal to a second overlap threshold, indicating that the association between BI industry data of each level in the data ring is strong, and generating a full-layer recommendation instruction;
the control query module is used for formulating a hierarchical control scheme according to the recommended instruction and querying target features in the data ring based on the hierarchical control scheme;
the hierarchical control scheme is an on-off control scheme of a data association channel between each hierarchy in the data ring, the on-off control of the data association channel changes along with the different recommended instructions, and the relevance of the data between each hierarchy in the data ring is controlled through the on-off control of the data association channel;
the hierarchical control scheme comprises a scheme for controlling the breakpoints at two ends of two data-associated channels to be conducted uniformly, a scheme for controlling the breakpoints at two ends of one data-associated channel to be conducted uniformly and a scheme for controlling the breakpoints at two ends of the two data-associated channels to be disconnected uniformly;
the method for making the scheme for controlling the breakpoints at two ends of two data-associated channels to be conducted uniformly and the scheme for controlling the breakpoints at two ends of one data-associated channel to be conducted uniformly comprises the following steps:
when the recommended instruction is a single-layer recommended instruction, describing that BI industry data of each layer in the data ring are not associated with each other, and making a scheme for controlling the disconnection of controllable interception points at two ends of two data association channels;
when the recommended instruction is a double-layer recommended instruction, two layers of BI industry data of each layer in the data ring are related, and a controllable cut-off point conduction scheme for controlling two ends of a data related channel is formulated;
when the recommended instruction is a full-layer recommended instruction, describing the mutual correlation between BI industry data of each layer in the data ring, and making a controllable cutoff point all-on scheme for controlling two ends of two data correlation channels;
it should be noted that, when a data association channel conduction scheme is formulated and controlled, it is necessary to determine whether the data association channel of the channel is a data association channel between the inner layer and the middle layer or a data association channel between the middle layer and the outer layer; when the target characteristic corresponding to the matching coincidence degree of the generated double-layer recommended instruction is a qualified production value, a data association channel between the inner layer and the middle layer is conducted; when the target characteristic corresponding to the matching coincidence degree of the generated double-layer recommended instruction is the revenue acceleration, a data association channel between the middle layer and the outer layer is conducted; when the target characteristic corresponding to the matching coincidence degree of the generated double-layer recommended instruction is an effective sales value, a data association channel among the inner layer, the middle layer and the outer layer is arbitrarily conducted;
in the embodiment, a multi-level data ring is constructed by collecting BI industry data of a selected enterprise, basic features of each level in the data ring are marked and divided into latent features and target features, simultaneously request features in request data of a user are marked, a request feature list is generated, then the request features in the request feature list are matched with the target features one by one, a recommendation instruction is generated based on a matching result, finally a level control scheme is formulated according to the recommendation instruction, and the target features in the data ring are queried based on the level control scheme to obtain required data; compared with the prior art, the BI industry data can be accurately identified, and after the request features of the user are matched with the target features, the relevancy recommendation instruction matched with the request features is generated, so that the BI industry data meeting the requirements in the data ring is accurately recommended in a small range, the recommendation of a large amount of irrelevant data is avoided, the query time of the user on the heart meter data is shortened, meanwhile, the BI industry data with different relevancy can be recommended according to the requirements of the user, the flexible switching of the relevancy between the BI industry data is realized, and the user is helped to quickly and accurately make excellent decisions for the enterprise development.
Example 2: referring to fig. 2, the detailed description of the embodiment is not provided in the description of embodiment 1, and a BI intelligent center method based on industrial big data is provided, which is applied to an intelligent server and implemented based on a BI intelligent center system based on industrial big data, and the method includes:
s1: collecting BI industry data of a selected enterprise;
s2: constructing a multi-level data ring based on BI industry data;
s3: marking basic features of each layer in the data ring, and dividing the basic features into latent features and target features;
s4: marking request features in the request data of the user, and generating a request feature list based on the request features;
s5: matching request features in the request feature list with target features one by one, and generating a recommendation instruction based on a matching result;
s6: and formulating a hierarchical control scheme according to the recommended instruction, and inquiring the target features in the data ring based on the hierarchical control scheme.
Example 3: referring to fig. 4, the disclosure provides an electronic device, including a processor and a memory;
wherein the memory stores a computer program for the processor to call;
the processor executes and realizes the BI intelligent center method based on the industrial big data by calling the computer program stored in the memory.
Since the electronic device described in this embodiment is an electronic device used to implement a BI intelligent center method based on industrial big data in embodiment 2 of the present application, based on a BI intelligent center method based on industrial big data described in this embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device and various modifications thereof, so how to implement the method in this embodiment of the present application for this electronic device will not be described in detail herein. As long as those skilled in the art implement an electronic device adopted by the BI intelligent center method based on industrial big data in the embodiments of the present application, the electronic device belongs to the scope of protection intended by the present application.
Example 4: referring to fig. 5, the present embodiment disclosure provides a computer readable storage medium having stored thereon a computer program that is erasable;
when the computer program is run, the method for realizing the BI intelligent center based on the industrial big data is executed.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. The BI intelligent center system based on industrial big data is applied to intelligent server, and is characterized in that the system comprises:
the industry data acquisition module acquires BI industry data of a selected enterprise;
the data ring construction module is used for constructing a multi-level data ring based on BI industrial data;
the construction method of the data ring comprises the following steps:
constructing blank inner layers, middle layers and outer layers, wherein the inner layers are positioned at the inner sides of the middle layers, and the outer layers are positioned at the outer sides of the middle layers;
respectively establishing a data association channel among the inner layer, the middle layer and the outer layer;
respectively setting a controllable cut-off point at two ends of the data association channel;
respectively importing a qualified production value, an effective sales value and a revenue increasing speed into an inner layer, a middle layer and an outer layer to construct a multi-level data ring;
the target feature dividing module marks basic features of each layer in the data ring, divides the basic features into latent features and target features, wherein the target features are basic features corresponding to BI industry data which can be directly queried and browsed in the current state in the data ring, and the latent features are basic features corresponding to BI industry data which cannot be directly queried and browsed in the current state in the data ring, and can query and browse the latent features corresponding to the target features only by querying and browsing the target features;
the request feature identification module marks request features in the request data of the user and generates a request feature list based on the request features;
the feature matching module is used for matching the request features in the request feature list with the target features one by one and generating a recommendation instruction based on a matching result;
the recommendation instructions comprise a single-layer recommendation instruction, a double-layer recommendation instruction and a full-layer recommendation instruction;
the recommendation method of the single-layer recommendation instruction, the double-layer recommendation instruction and the full-layer recommendation instruction comprises the following steps:
counting the occurrence times of qualified production features, effective sales features and revenue features in the feature phrase of the request data respectively;
comparing the occurrence times of the qualified production features, the effective sales features and the revenue features with the qualified production values, the effective sales values and the revenue accelerating storage amounts one by one respectively to obtain matching coincidence degrees;
comparing the matching coincidence degree with a preset first coincidence threshold value and a second coincidence threshold value, wherein the first coincidence threshold value is smaller than the second coincidence threshold value;
when the matching coincidence degree is smaller than a first coincidence threshold value, generating a single-layer recommendation instruction;
when the first coincidence threshold value is smaller than or equal to the matching coincidence degree and the matching coincidence degree is smaller than the second coincidence threshold value, generating a double-layer recommendation instruction;
when the matching overlap ratio is greater than or equal to a second overlap threshold, generating a full-layer recommendation instruction;
the control query module is used for formulating a hierarchical control scheme according to the recommended instruction and querying target features in the data ring based on the hierarchical control scheme;
the hierarchical control scheme comprises a scheme for controlling the breakpoints at two ends of two data-associated channels to be conducted uniformly, a scheme for controlling the breakpoints at two ends of one data-associated channel to be conducted uniformly and a scheme for controlling the breakpoints at two ends of the two data-associated channels to be disconnected uniformly;
the method for making the scheme for controlling the breakpoints at two ends of two data-associated channels to be conducted uniformly and the scheme for controlling the breakpoints at two ends of one data-associated channel to be conducted uniformly comprises the following steps:
when the recommended instruction is a single-layer recommended instruction, a scheme for controlling the disconnection of controllable interception points at two ends of the two data association channels is formulated;
when the recommended instruction is a double-layer recommended instruction, a controllable cutoff point conduction scheme for controlling two ends of a data association channel is formulated;
when the recommended instruction is a full-layer recommended instruction, a controllable cutting-off point all-on scheme for controlling two ends of the two data association channels is formulated.
2. The industry big data based BI intelligent center system of claim 1, wherein the BI industry data includes qualified production values, effective sales values, and revenue increases;
the method for acquiring the qualified production value comprises the following steps:
randomly selecting past enterprisesCounting periods, marking a period starting point and a period ending point, wherein the period starting point and the period ending point of any one counting period do not coincide with the period ending point of the previous counting period and the period starting point of the next counting period;
acquisition through industry big databaseCounting the total quantity of products and the quantity of qualified products in a period;
will beTotal amount of individual products>After the number of the qualified products is compared, the +.>Sub-qualification values;
the expression of the sub-fit value is:
;
in the method, in the process of the invention,is->Sub-fit values for a statistical period, +.>Is->The number of good products in a counting period,is->Counting the total amount of the products in a period;
at the position ofIn the sub-fit values, selecting +.>Sub-fit value, < ->Less than->And will->The sub-qualified values are accumulated and averaged to obtain qualified production values;
the expression of the qualified production value is:
;
in the method, in the process of the invention,for qualified production value, < >>Is->Sub-fit values.
3. The BI intelligent center system based on industrial big data according to claim 2, wherein the method for obtaining the effective sales value comprises:
acquisition through industry big databaseThe product volume and the product return volume of each sales area in the same sales period;
according toIndividual product volume sum->The product quantity is->A pre-sales value;
the expression for the pre-sales value is:
:
in the method, in the process of the invention,is->Pre-sales value of individual sales area, +.>Is->Product volume in sales area, +.>Is->Product returns for each sales area;
removing the maximum value and the minimum value of the pre-sales valueAccumulating the pre-sales values and then averaging to obtain an effective sales value;
the expression for the effective sales value is:
;
in the method, in the process of the invention,for effective sales value, ++>Is->A pre-sales value.
4. The BI intelligent center system based on industrial big data according to claim 3, wherein the revenue increasing acquisition method comprises:
acquiring past through enterprise financial statementA monthly sales amount and a monthly payout amount;
will beSales amount and->After comparison of the individual expenditure amounts, a +.>A monthly revenue amount;
the expression of the moon balance is:
;
in the method, in the process of the invention,is->The amount of nutrient receipts in one month->Is->Sales amount for month->Is->A monthly payout amount;
removing the month credit amount lower than the preset credit threshold value to obtainAn effective nutrient amount->Less than or equal to->;
Will beThe effective revenue amounts are accumulated and averaged to obtain the revenue acceleration;
the expression of the nutrient harvest acceleration is:
;
in the method, in the process of the invention,for increasing nutrient and nutrient, add->Is->And an effective credit amount.
5. The industry big data based BI intelligent center system of claim 4, wherein the method for partitioning the latency and target features comprises:
marking the total quantity of products, the quantity of qualified products, the sub-qualified value and the qualified production value in the inner layer of the data ring, and marking the total quantity of the products, the quantity of the sub-qualified values and the qualified production value as basic characteristics of the inner layer;
dividing the total quantity of products, the quantity of qualified products and the sub-qualified value into latent features of an inner layer, and dividing the qualified production value into target features of the inner layer;
marking the product volume, the product withdrawal volume, the pre-sales value and the effective sales value in the middle layer of the data ring as the basic characteristics of the middle layer;
dividing the product volume, the product withdrawal volume and the pre-sales value into middle-layer latent features, and dividing the effective sales value into middle-layer target features;
marking the month sales amount, the month expenditure amount, the month income amount and the income acceleration rate on the outer layer of the data ring, and recording the month sales amount, the month expenditure amount, the month income amount and the income acceleration rate as basic characteristics of the outer layer;
the monthly sales amount, the monthly expenditure amount and the monthly revenue amount are divided into the latency characteristics of the outer layer, and the revenue increasing speed is divided into the target characteristics of the outer layer.
6. The industry big data based BI intelligent center system of claim 5, wherein the request features include a qualified production feature, an effective sales feature, and a revenue feature;
the marking method of the qualified production characteristics, the effective sales characteristics and the revenue characteristics comprises the following steps:
traversing all feature phrases in the request data from the starting point of the request data;
marking the character phrase containing the word of 'qualified production' as the qualified production character;
marking the characteristic phrase containing the word of effective sales as effective sales characteristic;
the characteristic phrase containing the "nutrient" word is marked as nutrient characteristic.
7. The industry big data based BI intelligent center system of claim 6, wherein the request feature list generation method comprises:
sequentially numbering the involution production features, the effective sales features and the revenue features according to the sequence of the request feature marks;
and (3) arranging the numbers respectively belonging to the qualified production characteristics, the effective sales characteristics and the revenue characteristics in ascending order to generate a request characteristic list.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311753110.0A CN117435817B (en) | 2023-12-20 | 2023-12-20 | BI intelligent center system based on industry big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311753110.0A CN117435817B (en) | 2023-12-20 | 2023-12-20 | BI intelligent center system based on industry big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117435817A CN117435817A (en) | 2024-01-23 |
CN117435817B true CN117435817B (en) | 2024-03-15 |
Family
ID=89553787
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311753110.0A Active CN117435817B (en) | 2023-12-20 | 2023-12-20 | BI intelligent center system based on industry big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117435817B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108984711A (en) * | 2018-07-09 | 2018-12-11 | 湖南大学 | A kind of personalized APP recommended method based on layering insertion |
CN109902224A (en) * | 2019-01-17 | 2019-06-18 | 平安城市建设科技(深圳)有限公司 | Source of houses recommended method, device, equipment and medium based on user behavior analysis |
CN110119466A (en) * | 2019-03-29 | 2019-08-13 | 五渡(杭州)科技有限责任公司 | A kind of big data intelligent marketing system and method |
WO2020093289A1 (en) * | 2018-11-07 | 2020-05-14 | 深圳市欢太科技有限公司 | Resource recommendation method and apparatus, electronic device and storage medium |
CN112328873A (en) * | 2020-10-28 | 2021-02-05 | 苏州三六零智能安全科技有限公司 | Information recommendation method, device, equipment and storage medium |
CN114398477A (en) * | 2022-01-19 | 2022-04-26 | 平安国际智慧城市科技股份有限公司 | Policy recommendation method based on knowledge graph and related equipment thereof |
CN115048569A (en) * | 2022-01-27 | 2022-09-13 | 上海沐冉信息科技有限公司 | Method, device and equipment for accurately recommending big data and storage medium |
CN115809900A (en) * | 2022-12-05 | 2023-03-17 | 企知道网络技术有限公司 | Resource recommendation method, electronic device and storage medium |
CN116308657A (en) * | 2023-03-16 | 2023-06-23 | 浙江理工大学 | Commodity recommendation method and system for digital marketing platform |
CN116842269A (en) * | 2023-07-17 | 2023-10-03 | 企知道科技有限公司 | Policy recommendation method and device based on policy map and electronic equipment |
CN116910102A (en) * | 2023-07-19 | 2023-10-20 | 企知道科技有限公司 | Enterprise query method and device based on user feedback and electronic equipment |
-
2023
- 2023-12-20 CN CN202311753110.0A patent/CN117435817B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108984711A (en) * | 2018-07-09 | 2018-12-11 | 湖南大学 | A kind of personalized APP recommended method based on layering insertion |
WO2020093289A1 (en) * | 2018-11-07 | 2020-05-14 | 深圳市欢太科技有限公司 | Resource recommendation method and apparatus, electronic device and storage medium |
CN109902224A (en) * | 2019-01-17 | 2019-06-18 | 平安城市建设科技(深圳)有限公司 | Source of houses recommended method, device, equipment and medium based on user behavior analysis |
CN110119466A (en) * | 2019-03-29 | 2019-08-13 | 五渡(杭州)科技有限责任公司 | A kind of big data intelligent marketing system and method |
CN112328873A (en) * | 2020-10-28 | 2021-02-05 | 苏州三六零智能安全科技有限公司 | Information recommendation method, device, equipment and storage medium |
CN114398477A (en) * | 2022-01-19 | 2022-04-26 | 平安国际智慧城市科技股份有限公司 | Policy recommendation method based on knowledge graph and related equipment thereof |
CN115048569A (en) * | 2022-01-27 | 2022-09-13 | 上海沐冉信息科技有限公司 | Method, device and equipment for accurately recommending big data and storage medium |
CN115809900A (en) * | 2022-12-05 | 2023-03-17 | 企知道网络技术有限公司 | Resource recommendation method, electronic device and storage medium |
CN116308657A (en) * | 2023-03-16 | 2023-06-23 | 浙江理工大学 | Commodity recommendation method and system for digital marketing platform |
CN116842269A (en) * | 2023-07-17 | 2023-10-03 | 企知道科技有限公司 | Policy recommendation method and device based on policy map and electronic equipment |
CN116910102A (en) * | 2023-07-19 | 2023-10-20 | 企知道科技有限公司 | Enterprise query method and device based on user feedback and electronic equipment |
Non-Patent Citations (2)
Title |
---|
信令大数据技术在精准营销中的应用;王浩宇;孙启明;胡凯;;北京邮电大学学报(社会科学版);20160830(第04期);全文 * |
基于敏捷型BI的矿业集团生产信息分析模型;修国林;黄雨笋;李国清;胡乃联;侯杰;黄树巍;;中国矿业;20171015(第10期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117435817A (en) | 2024-01-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220292103A1 (en) | Information service for facts extracted from differing sources on a wide area network | |
US8504436B2 (en) | Systems and methods for generating a manufacturer tier product rollup | |
Shokouhi et al. | From queries to cards: Re-ranking proactive card recommendations based on reactive search history | |
CN103593350B (en) | Method and device for recommending promotion keyword price parameters | |
US20150213109A1 (en) | System and method for providing big data analytics on dynamically-changing data models | |
CN102999588A (en) | Method and system for recommending multimedia applications | |
US20090265325A1 (en) | Adaptive multi-channel content selection with behavior-aware query analysis | |
CN102760138A (en) | Classification method and device for user network behaviors and search method and device for user network behaviors | |
CN103309894B (en) | Based on search implementation method and the system of user property | |
CN113064866A (en) | Power business data integration system | |
CN105224529A (en) | A kind of personalized recommendation method based on user browsing behavior and device | |
CN106528804A (en) | User grouping method based on fuzzy clustering | |
US20210064592A1 (en) | Computer storage and retrieval mechanisms using distributed probabilistic counting | |
CN102270237A (en) | Method and system for detecting user source | |
CN117435817B (en) | BI intelligent center system based on industry big data | |
US20190108230A1 (en) | Automatic database analysis | |
An et al. | A two-stage multiple-factor aware method for travel product recommendation | |
CN104794237A (en) | Web page information processing method and device | |
WO2020001095A1 (en) | Context uncertainty elimination system based on hierarchical comprehensive quality index qox, and working method therefor | |
Zhang et al. | Discovering consumers’ purchase intentions based on mobile search behaviors | |
CN109241048A (en) | For the data processing method of data statistics, server and storage medium | |
CN117291494A (en) | Spare part inventory matching control method based on knowledge graph | |
CN110347923B (en) | Traceable fast fission type user portrait construction method | |
CN106919653A (en) | Daily record filter method based on user behavior | |
Zhao et al. | Improved collaborative filtering approach based on user similarity combination |
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 |