CN114048725A - Purchase content similarity evaluation method and storage medium - Google Patents

Purchase content similarity evaluation method and storage medium Download PDF

Info

Publication number
CN114048725A
CN114048725A CN202111260974.XA CN202111260974A CN114048725A CN 114048725 A CN114048725 A CN 114048725A CN 202111260974 A CN202111260974 A CN 202111260974A CN 114048725 A CN114048725 A CN 114048725A
Authority
CN
China
Prior art keywords
content
word
title
vector
segmentation
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
Application number
CN202111260974.XA
Other languages
Chinese (zh)
Inventor
赵立
罗建新
王传熙
陈颖华
郑敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujian Zefu Software Co ltd
Original Assignee
Fujian Zefu Software Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fujian Zefu Software Co ltd filed Critical Fujian Zefu Software Co ltd
Priority to CN202111260974.XA priority Critical patent/CN114048725A/en
Publication of CN114048725A publication Critical patent/CN114048725A/en
Pending legal-status Critical Current

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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Machine Translation (AREA)

Abstract

A method for evaluating similarity of purchased contents comprises the following steps of screening 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 word vector according to the first segmentation result, screening 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 word vector according to the second segmentation result, calculating cosine similarity or simple common word similarity of the word vector of the first core content and the word vector of the second core content, and taking a calculation result as similarity of the purchased contents. According to the technical scheme, the relevance among multiple purchasing processes can be rapidly judged through the analysis and comparison of the word vector attributes through the set purchasing descriptions.

Description

Purchase content similarity evaluation method and storage medium
Technical Field
The scheme relates to the field of paperless purchasing data, in particular to an evaluation method for similarity of purchasing contents and a storage medium.
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.
In a system for evaluating suppliers, an important ring is to quantify all purchasing items participated by the suppliers, and a scoring method for quantifying the similarity between different purchasing items is still lacked at present.
Disclosure of Invention
Therefore, it is necessary to provide an evaluation method capable of quantifying similarity between different procurement items
In order to achieve the above object, the inventor provides a method for evaluating similarity of purchased contents, comprising the steps of,
selecting core contents of the first purchase description to obtain first contents, performing text segmentation on the first contents to obtain first segmentation results, constructing a first word vector according to the first segmentation results, wherein the first word vector comprises all the segmentation words and word frequencies of all the segmentation words,
performing core content screening on the second purchase description to obtain second content, performing text word segmentation on the second content to obtain a second word segmentation result, constructing a second word vector according to the second word segmentation result, wherein the second word vector comprises each word segmentation and the word frequency of each word segmentation,
and calculating the cosine similarity or the simple common word similarity of the first core content word vector and the second core content word vector, and taking the calculation result as the purchasing content similarity.
In particular, the core content screening is carried out on the purchase description, comprising the steps of,
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.
In particular, the amount of the solvent to be used,
after the first content is subjected to text word segmentation, the part of speech tagging is also carried out to obtain a noun vector VtnAnd verb vector VtvAnd other word vectors VtoFiltering stop words and service common words;
after the second content is subjected to text word segmentation, the part of speech tagging is also carried out to obtain a noun vector VtnAnd verb vector VtvAnd other word vectors VtoAnd filtering stop words and service common words.
Specifically, the method further comprises the steps of increasing weights of a noun vector and a verb vector in the first content word vector; and increasing the weight of the noun vector and the verb vector in the second content word vector.
Specifically, the method further comprises the steps of performing title identification on the first content by adopting a regular expression, wherein the title comprises 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.
A purchase content similarity evaluation storage medium storing a computer program which, when executed, performs steps comprising,
selecting core contents of the first purchase description to obtain first contents, performing text segmentation on the first contents to obtain first segmentation results, constructing a first word vector according to the first segmentation results, wherein the first word vector comprises all the segmentation words and word frequencies of all the segmentation words,
performing core content screening on the second purchase description to obtain second content, performing text word segmentation on the second content to obtain a second word segmentation result, constructing a second word vector according to the second word segmentation result, wherein the second word vector comprises each word segmentation and the word frequency of each word segmentation,
and calculating the cosine similarity or the simple common word similarity of the first core content word vector and the second core content word vector, and taking the calculation result as the purchasing content similarity.
In particular, the computer program performs core content screening of the procurement specifications when being executed, and specifically performs the steps of,
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.
In particular a storage medium, which, when being executed,
the execution step carries out text word segmentation on the first content and then carries out step part-of-speech tagging to obtain a noun vector VtnAnd verb vector VtvAnd other word vectors VtoFiltering stop words and service common words;
the execution step carries out text word segmentation on the second content and then carries out step part-of-speech tagging to obtain a noun vector VtnAnd verb vector VtvAnd other word vectors VtoAnd filtering stop words and service common words.
Specifically, the computer program when executed further performs steps including, raising weights for a noun vector and a verb vector in the first content word vector; and increasing the weight of the noun vector and the verb vector in the second content word vector.
Specifically, the computer program when executed further performs a step of performing title recognition on the first content using a regular expression, the title including 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.
Different from the prior art, the technical scheme can compare the similarity of the purchasing contents of different times through the analysis and comparison of the word vector attributes through the set purchasing description, can quickly judge the correlation among multiple purchasing processes and provides reference for evaluating a purchasing system.
Drawings
Fig. 1 is a flowchart of a purchasing similarity evaluation method according to an embodiment.
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, the present embodiment provides a method for evaluating similarity of purchased content, 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 core content and the second core 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 other embodiments, core content screening is performed on the purchase specification, including the 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:
after the first content is subjected to text word segmentation, the steps are also carried out, the part of speech is labeled, and the first name can be obtained through calculationWord 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 method further comprises 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 method further comprises the steps of performing title identification on the first content by using a regular expression, wherein the title comprises 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 method for evaluating similarity of purchased content includes the following steps:
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.
Noun vector V formed by promoting word segmentation structure of title sentencetnAnd verb vector VtvAnd other word vectors VtoIs the word frequency multiplied by a weighting factor deltat (deltat)>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).
The proposal also provides a purchasing content similarity evaluation storage medium, which stores a computer program, wherein the computer program is executed when being executed and comprises the following steps,
selecting core contents of the first purchase description to obtain first contents, performing text segmentation on the first contents to obtain first segmentation results, constructing a first word vector according to the first segmentation results, wherein the first word vector comprises all the segmentation words and word frequencies of all the segmentation words,
performing core content screening on the second purchase description to obtain second content, performing text word segmentation on the second content to obtain a second word segmentation result, constructing a second word vector according to the second word segmentation result, wherein the second word vector comprises each word segmentation and the word frequency of each word segmentation,
and calculating the cosine similarity or the simple common word similarity of the first core content word vector and the second core content word vector, and taking the calculation result as the purchasing content similarity.
In particular, the computer program performs core content screening of the procurement specifications when being executed, and specifically performs the steps of,
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.
In particular a storage medium, which, when being executed,
the execution step carries out text word segmentation on the first content and then carries out step part-of-speech tagging to obtain a noun vector VtnAnd verb vector VtvAnd other word vectors VtoFiltering stop words and service common words;
the execution step carries out text word segmentation on the second content and then carries out step part-of-speech tagging to obtain a noun vector VtnAnd verb vector VtvAnd other word vectors VtoAnd filtering stop words and service common words.
Specifically, the computer program when executed further performs steps including, raising weights for a noun vector and a verb vector in the first content word vector; and increasing the weight of the noun vector and the verb vector in the second content word vector.
Specifically, the computer program when executed further performs a step of performing title recognition on the first content using a regular expression, the title including 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.
Different from the prior art, the technical scheme can compare the similarity of the purchasing contents of different times through the analysis and comparison of the word vector attributes through the set purchasing description, can quickly judge the correlation among multiple purchasing processes and provides reference for evaluating a purchasing system.
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 (10)

1. A method for evaluating similarity of purchased contents is characterized by comprising the following steps,
selecting core contents of the first purchase description to obtain first contents, performing text segmentation on the first contents to obtain first segmentation results, constructing a first word vector according to the first segmentation results, wherein the first word vector comprises all the segmentation words and word frequencies of all the segmentation words,
performing core content screening on the second purchase description to obtain second content, performing text word segmentation on the second content to obtain a second word segmentation result, constructing a second word vector according to the second word segmentation result, wherein the second word vector comprises each word segmentation and the word frequency of each word segmentation,
and calculating the cosine similarity or the simple common word similarity of the first core content word vector and the second core content word vector, and taking the calculation result as the purchasing content similarity.
2. The method for assessing similarity of purchased content according to claim 1, wherein the selection of core content for the purchase specification comprises the steps of,
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.
3. The purchasing content similarity evaluation method of claim 1,
after text word segmentation is carried out on the first content, part-of-speech tagging is carried out to obtain a first noun vector, a first verb vector and a first other word vector, and stop words and service common words are filtered;
and after the second content is subjected to text word segmentation, performing part-of-speech tagging to obtain a second noun vector, a second verb vector and second other word vectors, and filtering stop words and service common words.
4. The purchasing content similarity evaluation method according to claim 1, further comprising the steps of raising weights for a noun vector and a verb vector in the first content word vector; and increasing the weight of the noun vector and the verb vector in the second content word vector.
5. The purchasing content similarity evaluation method according to claim 3 or 4, characterized by further comprising the steps of performing title recognition on the first content by adopting a regular expression, wherein the title comprises 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.
6. A purchase content similarity evaluation storage medium storing a computer program which, when executed, performs steps comprising,
selecting core contents of the first purchase description to obtain first contents, performing text segmentation on the first contents to obtain first segmentation results, constructing a first word vector according to the first segmentation results, wherein the first word vector comprises all the segmentation words and word frequencies of all the segmentation words,
performing core content screening on the second purchase description to obtain second content, performing text word segmentation on the second content to obtain a second word segmentation result, constructing a second word vector according to the second word segmentation result, wherein the second word vector comprises each word segmentation and the word frequency of each word segmentation,
and calculating the cosine similarity or the simple common word similarity of the first core content word vector and the second core content word vector, and taking the calculation result as the purchasing content similarity.
7. The purchasing content similarity evaluation storage medium of claim 6, wherein the computer program, when executed, performs core content selection on the purchasing specification, and the specific implementation includes the steps of,
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.
8. The procurement content similarity evaluation storage medium of claim 6 characterized by, storage medium, the computer program, when executed,
performing text word segmentation on the first content, performing part-of-speech tagging to obtain a first noun vector, a first verb vector and a first other word vector, and filtering stop words and service common words;
and performing text word segmentation on the second content, performing part-of-speech tagging to obtain a second noun vector, a first verb vector and a second other word vector, and filtering stop words and service common words.
9. The procurement content similarity evaluation storage medium of claim 6 wherein the computer program, when executed, further performs steps comprising, for a noun vector and a verb vector in a first content word vector, raising a weight; and increasing the weight of the noun vector and the verb vector in the second content word vector.
10. The procurement content similarity evaluation storage medium of claim 8 or 9 characterized by, the computer program when executed further performs the steps of, for the first content, employing a regular expression for title identification, the title comprising a major title, a minor title, a major title, and a minor 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.
CN202111260974.XA 2021-10-28 2021-10-28 Purchase content similarity evaluation method and storage medium Pending CN114048725A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111260974.XA CN114048725A (en) 2021-10-28 2021-10-28 Purchase content similarity evaluation method and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111260974.XA CN114048725A (en) 2021-10-28 2021-10-28 Purchase content similarity evaluation method and storage medium

Publications (1)

Publication Number Publication Date
CN114048725A true CN114048725A (en) 2022-02-15

Family

ID=80206312

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111260974.XA Pending CN114048725A (en) 2021-10-28 2021-10-28 Purchase content similarity evaluation method and storage medium

Country Status (1)

Country Link
CN (1) CN114048725A (en)

Similar Documents

Publication Publication Date Title
US10282468B2 (en) Document-based requirement identification and extraction
Abrahams et al. An integrated text analytic framework for product defect discovery
CN110210952B (en) Bidding evaluation method and device
US10579651B1 (en) Method, system, and program for evaluating intellectual property right
US20150339616A1 (en) System for real-time suggestion of a subject matter expert in an authoring environment
CN109033132B (en) Method and device for calculating text and subject correlation by using knowledge graph
WO2023050491A1 (en) Business opportunity mining method and apparatus, and computer device and storage medium
CN111563377A (en) Data enhancement method and device
US20150339310A1 (en) System for recommending related-content analysis in an authoring environment
Liu et al. Product optimization design based on online review and orthogonal experiment under the background of big data
CN113672705A (en) Resume screening method, apparatus, device, medium and program product
CN114066177A (en) Supplier scoring method and storage medium
CN114065725A (en) Purchasing big data management system
CN112668838A (en) Scoring standard word bank establishing method and device based on natural language analysis
Siddiqui et al. Quality Prediction of Wearable Apps in the Google Play Store.
CN114048725A (en) Purchase content similarity evaluation method and storage medium
Groher et al. Leveraging AI-based decision support for opportunity analysis
JP5340847B2 (en) Document data processing device
Pataci et al. Stock price volatility prediction: A case study with AutoML
KR20230103025A (en) Method, Apparatus, and System for provision of corporate credit analysis and rating information
Azad et al. Business data enrichment: Issues and challenges
Tseng et al. An intelligent disease query system based on RASA NLU
Chung et al. A question detection algorithm for text analysis
CN114399343B (en) Intelligent robot online auxiliary selling method and system
CN115600586B (en) Abstract text generation method, computing device 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