CN114065725A - Purchasing big data management system - Google Patents
Purchasing big data management system Download PDFInfo
- Publication number
- CN114065725A CN114065725A CN202111261783.5A CN202111261783A CN114065725A CN 114065725 A CN114065725 A CN 114065725A CN 202111261783 A CN202111261783 A CN 202111261783A CN 114065725 A CN114065725 A CN 114065725A
- Authority
- CN
- China
- Prior art keywords
- content
- purchasing
- procurement
- similarity
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
Abstract
The utility model provides a purchase big data management system, includes following module, storage module is used for storing purchase information, purchase information includes the purchase description, still is used for storing the purchase content similarity between at least two purchase information, purchase similarity value calculation module is used for the execution step, carries out core content screening to first purchase description, obtains first content, carries out text segmentation to first content, obtains first segmentation result, according to first segmentation result constitutes first content word vector, first content word vector includes the word frequency of each segmentation and each segmentation. The technical scheme can store a plurality of purchasing information, calculate the similarity of the purchasing contents among the nodes and quickly judge the correlation among the multiple purchasing processes.
Description
Technical Field
The invention relates to the field of purchasing data management, in particular to a management system relating to purchasing big data.
Background
The enterprise informatization construction improves the production operation efficiency of enterprises through the deployment of computer technology, reduces operation risks and cost, and accordingly improves the overall management level and continuous operation capacity of the enterprises. At present, various informationized systems are purchased by a plurality of enterprises in a purchasing mode, the quality of an enterprise purchasing informatization system supplier is closely related to the success or failure of an informationized project, the survival and sustainable development of the enterprises are determined to a great extent by the selection of the purchasing supplier and the establishment of a purchasing contract, and therefore how to evaluate the suppliers becomes a research subject.
At present, the enterprise basically establishes corresponding qualification conditions for the evaluation of suppliers, and then adopts experts to evaluate various materials provided by the suppliers, wherein the materials comprise: enterprise qualification, purchasing system soft copy, purchasing system demonstration and the like. But management of records relating to supplier and procurement processes has not yet been established.
Disclosure of Invention
For this reason, it is necessary to provide a scheme capable of systematically and scientifically managing procurement of large data.
In order to achieve the above object, the inventor provides a purchasing big data management system, which includes a storage module, wherein the storage module is used for storing purchasing information, the purchasing information includes purchasing instruction, and is also used for storing purchasing content similarity between at least two pieces of purchasing information,
a purchase similarity value calculation module for performing steps of selecting core contents of a first purchase description to obtain a first content, performing text segmentation on the first content to obtain a first segmentation result, constructing a first content word vector according to the first segmentation result, wherein the first content word vector comprises each segmentation and word frequency of each segmentation, selecting core contents of a second purchase description to obtain a second content, performing text segmentation on the second content to obtain a second segmentation result, constructing a second core content word vector according to the second segmentation result, wherein the second content word vector comprises each segmentation and word frequency of each segmentation,
the purchasing similarity value calculating module is used for calculating the purchasing content similarity according to the cosine similarity or the simple common word similarity of the first content word vector and the second content word vector.
Specifically, the storage module is further used for storing enterprise information and storing the association between the purchasing information and the participating enterprises.
Specifically, after receiving the new purchasing information, the storage module calculates the similarity of the purchasing content between the new purchasing information and the stored purchasing information and stores the similarity of the purchasing content between the new purchasing information and the stored purchasing information if the participating enterprise of the new purchasing information is the same as at least one participating enterprise of the stored purchasing information.
Specifically, after receiving the new purchasing information, the storage module calculates the purchasing content similarity between the new purchasing information and the stored purchasing information, and stores the purchasing content similarity between the new purchasing information and the stored purchasing information.
And further, the purchasing similarity value calculation module is used for screening core contents of the purchasing specification, and specifically comprises the steps of identifying templated contents in the purchasing specification, including bid-inviting announcement, bid-inviting need to know, contract clauses and bid document format requirements, and deleting the templated contents to obtain the screened contents.
Specifically, part-of-speech tagging is performed to raise weights for the noun vector and the verb vector in the first content word vector and the second content word vector.
The system further comprises a title identification module, wherein the title identification module is used for carrying out title identification on the first content and the second content by adopting a regular expression, and the title comprises a main title, a sub-title, a main title and a sub-title; the title is subjected to word segmentation and part-of-speech tagging,
the purchasing similarity value calculation module is used for adding weight to a word vector obtained by segmenting a title sentence in the first content word vector; and the second content word vector is used for adding weight to the title sentence word segmentation vector in the second content word vector.
And further, the system also comprises a supplier scoring module, wherein the supplier scoring module is used for calculating the supplier scoring among the enterprises relative to the purchase information participated by the enterprises according to preset rules.
Specifically, the storage module is further used for storing the supplier scores among the enterprises and the purchasing information participated by the enterprises.
Different from the prior art, the technical scheme can store a plurality of pieces of purchasing information, each piece of purchasing information is used as a node, the purchasing description in the purchasing information is used as a basis, and the similarity of purchasing contents among the nodes can be calculated, so that the correlation among multiple purchasing processes can be rapidly judged, and reference is provided for integrally evaluating a purchasing system.
Drawings
FIG. 1 is a block diagram of a procurement big data management system according to an embodiment;
fig. 2 is a diagram of a method for calculating similarity of procurement contents according to an embodiment.
Description of reference numerals:
101. a storage module for storing the data of the data,
102. a purchase similarity value calculation module;
103. a supplier scoring module.
Detailed Description
To explain technical contents, structural features, and objects and effects of the technical solutions in detail, the following detailed description is given with reference to the accompanying drawings in conjunction with the embodiments.
Referring to fig. 1, a purchasing big data management system includes a storage module 100 for storing purchasing information including purchasing specifications and purchasing content similarity between at least two pieces of purchasing information,
a purchase similarity value calculation module 102 for performing the steps, selecting the core content of the first purchase description to obtain a first content, performing text segmentation on the first content to obtain a first segmentation result, constructing a first content word vector according to the first word segmentation result, wherein the first content word vector comprises each word segmentation and the word frequency of each word segmentation, screening the second purchase description for core content to obtain second content, performing text word segmentation on the second content to obtain a second word segmentation result, constructing a second kernel content word vector according to the second word segmentation result, wherein the second content word vector comprises each word segmentation and the word frequency of each word segmentation, the purchasing similarity value calculating module is used for calculating the purchasing content similarity according to the cosine similarity or the simple common word similarity of the first content word vector and the second content word vector.
According to the technical scheme, the plurality of purchasing information can be stored, each purchasing information is used as a node, the purchasing description in the purchasing information is used as a basis, and the similarity of the purchasing contents among the nodes can be calculated, so that the correlation among multiple purchasing processes can be rapidly judged, and reference is provided for integrally evaluating a purchasing system.
Referring to fig. 2, the purchasing similarity value calculating module 102 of the present embodiment is used to execute the purchasing content similarity evaluation method, including the following steps,
s101, performing core content screening on a first purchase description to obtain a first content, performing text segmentation on the first content to obtain a first segmentation result, constructing a first word vector according to the first segmentation result, wherein the first word vector comprises each segmentation and the word frequency of each segmentation, S102, performing core content screening on a second purchase description to obtain a second content, performing text segmentation on the second content to obtain a second segmentation result, constructing a second word vector according to the second segmentation result, wherein the second word vector comprises each segmentation and the word frequency of each segmentation, and S103, calculating the cosine similarity or the simple common word similarity of the word vectors of the first content and the second content, and taking the calculation result as the purchase content similarity.
The purchasing description may be a more main file recording the purchasing characteristics in the purchasing process, and specifically, the recording file of the purchasing characteristics may include a purchasing bid file or a purchasing demand document. The first procurement specification corresponds to a first procurement process, and the second procurement specification corresponds to a second procurement process. Whether the procurement process succeeds in bidding or not, the related documents can be stored and analyzed according to the scheme. The method analyzes and compares the word vectors appearing in the purchasing description, and the word vectors approximately approximate to the purchasing related documents have higher similarity.
According to the technical scheme, the similarity of the purchasing contents of different times can be compared through the analysis and comparison of the word vector attributes through the set purchasing descriptions, the correlation among multiple purchasing processes can be rapidly judged, and reference is provided for evaluating a purchasing system. In some embodiments of the purchase data management system, when the purchase information is recorded and calculated, the new purchase information can be used as a node, the similarity between the new purchase information and the purchase content of all the existing purchase information nodes can be stored, and a storage data relationship, which is related to the node through the similarity between the purchase content and the node, is established.
In other specific embodiments, the purchase similarity value calculation module 102 is used for core content screening of the purchase specification, and includes steps,
and identifying the templatized contents in the purchase specification, including bid notice, bid requisition, contract clause and bid document format requirements, and deleting the templatized contents to obtain the first contents. Identifying templatized content in the purchase specification can be accomplished by identifying paragraph keywords. The applicant finds that in practical application, the templated contents about the purchase instruction are all different and have more similar word segmentation structures, and the incorporation of the templated contents into the evaluation system may result in an improper increase in similarity value. Therefore, by identifying and deleting the woodcut content and screening the core content, the influence of the templated content in the purchase description on the similarity judgment can be better eliminated, and the technical effect of better evaluating the similarity is achieved.
In other specific embodiments, in order to further exclude noise in the word segmentation result, the applicant further sets the following scheme:
the purchasing similarity value calculating module 102 performs text segmentation on the first content, then performs the steps of part-of-speech tagging and calculating to obtain a first noun vector VtnAnd a first verb vector VtvAnd a first other word vector VtoFiltering stop words and service common words; after the second content is subjected to text word segmentation, the step of part of speech tagging is also carried out to obtain a second noun vector VtnAnd a second verb vector VtvAnd a second other word vector VtoAnd filtering stop words and service common words. In this embodiment, part-of-speech tagging is helpful for distinguishing parts of speech of each participle, and filtering stop words and common service words can also avoid that the common service words with the same size and different sizes affect similarity determination, where the common service words in some embodiments, such as common words of software information-based construction projects, include: high cohesion, low coupling, microservice, etc. Common words in the business field can be labeled manually. And then noise can be eliminated, and the similarity of different purchase descriptions can be better compared.
In some other specific embodiments, the procurement similarity value calculation module 102 is further configured to perform the step of raising the weight of the second noun vector and the second verb vector in the first content word vector; and increasing the weight of the second noun vector and the second verb vector in the second content word vector. In the core content of purchasing, the unique characteristic is that variable nouns and verbs in the core content are purchased, so that the weight improvement of the nouns and the verbs is beneficial to distinguishing different purchasing description contents, and further the judgment of purchasing similarity is more scientific and effective.
In other specific embodiments, the purchasing similarity value calculating module 102 is further configured to perform a step of performing title identification on the first content by using a regular expression, where the title includes a main title, a sub-title, a main title and a sub-title; performing word segmentation and part-of-speech tagging on a title to form a first title sentence word vector, and adding weight to the first title sentence word vector in the first content word vector; adopting a regular expression to identify the second content, wherein the title comprises a main title, a sub-title, a main title and a sub-title; and performing word segmentation and part-of-speech tagging on the title to form a second title sentence word vector, and adding weight to the second title sentence word vector in the first content word vector. The title recognition is beneficial to positioning and controlling the main content of the purchasing explanation, the text title can be recognized more accurately and efficiently through the regular expression, the weight is added to the word vector contained in the title after the title is recognized, the key word segmentation in the purchasing explanation can be highlighted, the judgment of the similarity is more scientific, and the similarity score can reflect the similarity of different purchasing explanations.
In other embodiments, the purchasing similarity value calculation module 102 is further configured to perform steps including:
rejecting the templated content of the bidding document, such as: bidding announcement, bidding requisition, contract terms, bidding document format requirements, bid evaluation method and the like.
Each sentence of the purchase content processing in the bidding document is subjected to title recognition by adopting a regular expression to form a title list Tl. Then, the title sentence is divided into words and labeled with part of speech to form a noun vector VtnAnd verb vector VtvAnd other word vectors VtoThe dimension of the vector is the union of the unrepeated words, and the weight of each dimension is the word frequency.
Performing word segmentation and part-of-speech tagging on each other sentence of the purchase content in the bidding document to form a noun vector VcnAnd verb vector VcvAnd other word vectors VcoThe dimension of the vector is the union of the unrepeated words, and the weight of each dimension is the word frequency.
Stop words are filtered out.
Filtering out common words in the service field, such as common words in software information construction projects: high cohesion, low coupling, microservice, etc. Common words in the business field can be labeled manually.
Raising the word of the title sentence to form a noun vector VtnAnd verb vector VtvAnd other word vectors VtoEach dimension of (1) is weighted byWord frequency multiplied by a weighting coefficient Δ t (Δ t)>Title importance higher than body content).
Combining word vectors formed by other contents of the title and the text and adding each dimension weight value of the same word to obtain:
noun word vector: vn is Vtn∪Vcn
Verb word vector: vt ═ Vtv∪Vcv
Other word and word vectors: vo is Vto∪Vco
Elevated name word vector VnAnd verb word vector VtThe weight of each dimension in (i.e. the noun word vector V)nThe weighted value of each dimension is word frequency multiplied by delta n, verb word vector VtThe weight value of each dimension is the word frequency multiplied by Δ v (Δ n)>1,Δv>1, the procurement core content mostly takes nouns and verbs as main parts, so the weight of the nouns and the verbs is improved).
Merged name word vector VnVerb word vector VtAnd the other word vectors Vo form a final procurement tender document word vector V.
And processing the bidding documents of two purchases to be compared according to the steps to obtain two purchase word vectors which are respectively recorded as: viAnd Vj. Cosine similarity or simple common words of the word vectors are calculated as the similarity C (i, j).
In other specific embodiments, the storage module 101 is further configured to store business information and further store a relationship between purchasing information and participating businesses. The storage module is arranged to store the purchasing information and participate in the relation between the enterprises, so that the node network in the purchasing data management system can be more perfect, the related purchasing information and purchasing content similarity can be called to calculate when the enterprise information is calculated, and the enterprises can be connected in series through the purchasing information.
In other specific embodiments, after receiving the new purchasing information, if the participating enterprise of the new purchasing information is the same as at least one participating enterprise of the stored purchasing information, the storage module 101 calculates the similarity of the purchasing content between the new purchasing information and the stored purchasing information, and stores the similarity of the purchasing content between the new purchasing information and the stored purchasing information. For example, the storage module stores the purchasing information a and b, wherein A, B, C is provided for participating enterprises of the purchasing information a, D, E, F is provided for participating enterprises of the purchasing information b, and at this time, the similarity of purchasing contents does not need to be calculated to connect a and b, and only when the purchasing information c is newly entered, C, G, H is provided for participating enterprises of the storing system which retrieves the purchasing information c, at this time, the connection between the purchasing information c and a needs to be established, so that the similarity of purchasing contents between the purchasing information c and the purchasing information a is calculated, and the similarity of purchasing contents between the purchasing information c and the purchasing information b still does not need to be calculated and stored. The calculation of the similarity of the purchasing contents is only carried out and stored among the purchasing information which participates in the enterprise and is linked, so that the calculation amount and the data storage amount required by the data management system are saved, and the operation of the purchasing data management system is more efficient.
In other embodiments, the storage module calculates the similarity of the purchasing content between the new purchasing information and the stored purchasing information after receiving the new purchasing information, and stores the similarity of the purchasing content between the new purchasing information and the stored purchasing information. The content similarity between the new purchase information and all the stored purchase information is recorded, so that the purchase information can be recorded more completely and specifically in an all-around manner.
In some other further embodiments, the procurement data management system further comprises a supplier scoring module 103 for calculating a supplier score between the enterprise with respect to the respective procurement information with which it participates, according to preset rules. The preset rule can be determined by the user, for example, the degree of adaptation between the supplier and the specific purchasing information is calculated based on the purchasing content similarity of the purchasing information participated by the supplier enterprise. By scoring the supplier with respect to the specific purchasing information, the degree of matching between the supplier and the specific purchasing information can be better displayed, which contributes to the enhancement of the sunshine and transparency of the purchasing data.
In some further embodiments, the storage module 101 is further configured to store supplier scores between the enterprises and the procurement information involved by the enterprises. Storing the supplier scores can further refine the data of the procurement data management system.
In other embodiments, the supplier scoring module 103 is also performed by the user, S1 calculates purchase content similarity, S2 calculates supplier service similarity, S3 calculates supplier business score, calculates supplier bid offer matching,
s4, calculating the total score of the first supplier, wherein the total score of the first supplier is positively correlated with the similarity of the purchasing content, the similarity of the service content of the supplier, the business score of the supplier and the matching degree of the bid and offer of the supplier.
The purchasing content similarity is the similarity between the historical purchasing content of the supplier and the purchasing content at this time, the supplier service similarity is a numerical value obtained by considering the time factor of the historical purchasing content of the supplier, and the supplier quotation matching degree is a numerical value obtained by considering the purchasing content similarity in the quotation of the supplier. In some embodiments, the supplier's score Ai ═ SCi Δ C + ECi Δ E + PCi Δ P may be set.
And traversing all the suppliers participating in the bidding, and respectively calculating the purchasing content similarity SCi of the suppliers, the commercial grade value ECi of the suppliers and the bidding quotation matching degree PCi of the suppliers. Δ C, Δ E, Δ P are weight values.
The proposal provides the grading method of the supplier, can improve the automation degree, provides reference for a user to select a buyer and can improve the automation degree and the fairness of a program to the supplier selection.
The method for calculating the similarity of the provider service by the provider scoring module 103 comprises the following steps:
and acquiring the similarity of the single-time purchasing content of past bids participated by the first supplier, and summing the results of multiplying the similarity of the single-time purchasing content of the past bids by the correction factor of the time of the past bids to obtain the service similarity of the supplier, wherein the correction factor of the time of the past bids is positively correlated with the occurrence time of the past bids. In some specific embodiments, the calculation manner of the provider service similarity may be:
1) the initialization supplier purchases content similarity SC to be 0.
2) And traversing each bid participated by the supplier to calculate the similarity of the contents of single purchase, marking the similarity as Ci, and calculating a time correction factor Ti of each purchase.
3) And accumulating the supplier purchase content similarity, wherein SC + Ci Ti.
4) The final accumulated value SC provider purchases content similarity.
The time correction factor is positively correlated with the occurrence time of the past bids, and the value of the time correction factor is larger when the occurrence time of a certain bid is closer to the current time. Considering that bid contents, supplier qualifications, etc. may vary with time and their reference values in the bidding process may be weaker and weaker with the lapse of time, a time correction factor T is introduced for an entity having a time factor. In some embodiments, the time correction factor T is defined as follows:
1) the base time was defined as 1970, 1, 0 o 0, 0 min 0 s.
2) Time difference Δ Ta between the bidding time of history bid a and the reference time is calculated in units of seconds.
3) And calculating the time difference delta T between the current bidding time and the reference time, wherein the unit is second.
4) Then T is Δ Ta/Δ T.
The reference time can be set according to the needs. In other specific embodiments of the present invention,
the time correction factor Ti during the ith time casting meets the following requirements:
Ti＝(ti-t0)/(tc-t0)
ti is the ith bidding time, tc is the current bidding time, and t0 is the reference time constant. By the time correction factor, the purchasing process closer to the current time has a higher influence value, so that the problem of the practicability of the supplier scoring is better solved.
In some further embodiments, the method for calculating the matching degree of the bid price of the supplier by the supplier scoring module 103 comprises the following steps,
the method comprises the steps of obtaining the similarity of the contents of the past bidding purchases participated by a first supplier, obtaining the offers of the past bidding quotations participated by the first supplier, obtaining the matching degree of the offers of the past bidding quotations according to the matching degree of the offers of the bidding quotations which is equal to the similarity of the contents of the bidding purchases/the offers of the bidding quotations, summing up the results of the matching degree of the offers of the past bidding quotations and the correction factor of the time of the past bidding quotations to obtain the matching degree of the bidding prices of the suppliers, wherein the correction factor of the time of the past bidding is positively correlated with the occurrence time of the past bidding.
As in some embodiments, the solution performs a calculation of the bid match:
the algorithm for calculating the matching degree of the single bid quotation is as follows:
1) obtaining the bid price Pi of supplier participation
2) And calculating the similarity Ci of the single-purchase content.
3) Calculating the matching degree delta P of the single bid price based on the similarity of the purchased content, wherein the calculation formula is as follows: and P is Ci/Pi.
The supplier bid matching degree calculation algorithm is as follows:
1) the supplier bid matching degree PC is initialized to 0.
2) And calculating the single quote matching degree delta Pi by traversing each bid participated by the supplier, and simultaneously calculating the time correction factor Ti of each purchase.
3) The accumulated supplier bid price match PC + Δ Pi Ti. And finishing the accumulation of the results of multiplying all the single quotation matching degrees by the time correction factor. Through the arrangement, the purchasing process closer to the current time has a higher influence value, so that the bidding price matching degree of the supplier is quantized, and the problem of the practicability of the grading of the supplier is better solved.
In other embodiments, the method further comprises the following steps of calculating the bid-business score of the bid-business score calculation provider according to the bid-business score calculation algorithm:
1) the initial provider business score evaluation value EC is 0.
2) And traversing each bid participated by the supplier to obtain a business scoring value, wherein the business scoring value refers to the business scoring value obtained by scoring according to a method specified in the business scoring in the bidding document after the enterprise participated in the bid scoring. If not, the system is normalized to the percentage system and is recorded as Ei, and a time adjustment factor Ti of each purchase is calculated.
3) And accumulating the supplier purchase content similarity, EC + Ci Ti.
4) And the final accumulated value EC is a bidding business evaluation value. Through the arrangement, the purchasing process closer to the current time has a higher influence value, so that the current business scoring value of the supplier is quantized, and the problem of the practicability of the scoring of the supplier is solved better.
It should be noted that, although the above embodiments have been described herein, the invention is not limited thereto. Therefore, based on the innovative concepts of the present invention, the technical solutions of the present invention can be directly or indirectly applied to other related technical fields by making changes and modifications to the embodiments described herein, or by using equivalent structures or equivalent processes performed in the content of the present specification and the attached drawings, which are included in the scope of the present invention.
Claims (9)
1. The purchasing big data management system is characterized by comprising a module and a storage module, wherein the storage module is used for storing purchasing information, the purchasing information comprises purchasing specifications and is also used for storing purchasing content similarity between at least two pieces of purchasing information,
a purchase similarity value calculation module for performing steps of selecting core contents of a first purchase description to obtain a first content, performing text segmentation on the first content to obtain a first segmentation result, constructing a first content word vector according to the first segmentation result, wherein the first content word vector comprises each segmentation and word frequency of each segmentation, selecting core contents of a second purchase description to obtain a second content, performing text segmentation on the second content to obtain a second segmentation result, constructing a second core content word vector according to the second segmentation result, wherein the second content word vector comprises each segmentation and word frequency of each segmentation,
the purchasing similarity value calculating module is used for calculating the purchasing content similarity according to the cosine similarity or the simple common word similarity of the first content word vector and the second content word vector.
2. The procurement big data management system of claim 1 characterized by, the storage module is further configured to store business information, and further store associations between procurement information and participating businesses.
3. The procurement big data management system of claim 2 characterized by, the storage module, after receiving new procurement information, if the participating enterprise of new procurement information is the same as at least one participating enterprise of stored procurement information, then calculates the procurement content similarity between the new procurement information and the stored procurement information and saves the procurement content similarity between the new procurement information and the stored procurement information.
4. The procurement big data management system of claim 1 characterized by, the storage module, after receiving new procurement information, calculates the procurement content similarity between the new procurement information and the stored procurement information, and saves the procurement content similarity between the new procurement information and the stored procurement information.
5. The procurement big data management system of claim 1, characterized by, that the procurement similarity value calculation module is used to screen core content for the procurement specifications, specifically comprising the steps of identifying templated content in the procurement specifications, including bid announcement, bid requisition, contract terms, and bid document format requirements, deleting the templated content, and obtaining the screened content.
6. The procurement big data management system of claim 1 characterized by, making part-of-speech tags, raising weights for noun vectors and verb vectors in the first content word vector and the second content word vector.
7. The procurement big data management system of claim 1 characterized by, further comprising a title identification module, the title identification module is used for title identification of the first content and the second content using regular expressions, the title comprises a big title, a small title, a main title and a sub-title; the title is subjected to word segmentation and part-of-speech tagging,
the purchasing similarity value calculation module is used for adding weight to a word vector obtained by segmenting a title sentence in the first content word vector; and the second content word vector is used for adding weight to the title sentence word segmentation vector in the second content word vector.
8. The procurement big data management system of claim 1 characterized by, further comprising a supplier rating module for calculating a supplier rating between the enterprise and each procurement information it participates in according to preset rules.
9. The procurement big data management system of claim 8 characterized by, the storage module is further configured to store supplier ratings between businesses and procurement information the businesses participate in.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111261783.5A CN114065725A (en) | 2021-10-28 | 2021-10-28 | Purchasing big data management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111261783.5A CN114065725A (en) | 2021-10-28 | 2021-10-28 | Purchasing big data management system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114065725A true CN114065725A (en) | 2022-02-18 |
Family
ID=80235729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111261783.5A Pending CN114065725A (en) | 2021-10-28 | 2021-10-28 | Purchasing big data management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114065725A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290799A (en) * | 2023-11-24 | 2023-12-26 | 山东壹知产数字科技有限公司 | Enterprise purchase management method and system based on big data |
-
2021
- 2021-10-28 CN CN202111261783.5A patent/CN114065725A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117290799A (en) * | 2023-11-24 | 2023-12-26 | 山东壹知产数字科技有限公司 | Enterprise purchase management method and system based on big data |
| CN117290799B (en) * | 2023-11-24 | 2024-02-02 | 山东壹知产数字科技有限公司 | Enterprise purchase management method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mohd Thas Thaker et al. | What keeps Islamic mobile banking customers loyal? | |
| Leung et al. | Internet marketing research in hospitality and tourism: a review and journal preferences | |
| US7403911B2 (en) | Method and system for setting an optimal preference policy for an auction | |
| Chen et al. | The determinants of online customer ratings: a combined domain ontology and topic text analytics approach | |
| JP2014522072A (en) | Content information recommendation based on user behavior | |
| US20220343433A1 (en) | System and method that rank businesses in environmental, social and governance (esg) | |
| US11803927B2 (en) | Analysis of intellectual-property data in relation to products and services | |
| US20100332434A1 (en) | Data classification tool using dynamic allocation of attribute weights | |
| US20210004920A1 (en) | Analysis Of Intellectual-Property Data In Relation To Products And Services | |
| US20210004918A1 (en) | Analysis Of Intellectual-Property Data In Relation To Products And Services | |
| WO2023050491A1 (en) | Business opportunity mining method and apparatus, and computer device and storage medium | |
| Gregg et al. | Factors affecting the long-term survival of eBay ventures: a longitudinal study | |
| CN112446629A (en) | Knowledge graph-based supplier selection method | |
| CN112150291A (en) | Intelligent financial product recommendation system | |
| JP2022538925A (en) | Analysis of intellectual property data related to products and services | |
| Nastisin et al. | Sustainable performance of players in the global aviation industry in the light of multi-factor analysis of online reputation | |
| CN114065725A (en) | Purchasing big data management system | |
| Liang et al. | The screening role of design parameters for service procurement auctions in online service outsourcing platforms | |
| CN114066177A (en) | Supplier scoring method and storage medium | |
| CN112132396A (en) | Customer relationship distribution method and system based on intelligent matching | |
| Xing et al. | Pricing and sample set strategies of data providers under quality information asymmetry | |
| CN110443646B (en) | Product competition relation network analysis method and system | |
| CN115700705A (en) | Product analysis method and device, electronic equipment and readable storage medium | |
| Pataci et al. | Stock price volatility prediction: A case study with AutoML | |
| CN114048725A (en) | Purchase content similarity evaluation method and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |