CN113495947A - Work order searching method and device and computing equipment - Google Patents
Work order searching method and device and computing equipment Download PDFInfo
- Publication number
- CN113495947A CN113495947A CN202010269941.0A CN202010269941A CN113495947A CN 113495947 A CN113495947 A CN 113495947A CN 202010269941 A CN202010269941 A CN 202010269941A CN 113495947 A CN113495947 A CN 113495947A
- Authority
- CN
- China
- Prior art keywords
- work order
- searched
- query
- entries
- entry
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000011218 segmentation Effects 0.000 claims abstract description 30
- 238000012163 sequencing technique Methods 0.000 claims abstract description 4
- 238000004891 communication Methods 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
- G06F16/325—Hash tables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90348—Query processing by searching ordered data, e.g. alpha-numerically ordered data
-
- 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
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention relates to the technical field of network search, and discloses a work order search method, a work order search device and computing equipment. The method comprises the following steps: receiving a recommendation request; acquiring a current work order according to the recommendation request; performing word segmentation on the current work order according to a preset word segmentation word bank to obtain a plurality of entries to be searched; determining the weight of each entry to be searched; sequencing all the entries to be searched according to the sequence of the weights of the entries to be searched from large to small; according to a preset query dictionary, sequentially searching the entries to be searched according to the sequence to obtain target work orders corresponding to the entries to be searched; and displaying the target work order according to the grade of the target work order. Through the mode, the method and the device can improve the accuracy of the search result.
Description
Technical Field
The embodiment of the invention relates to the technical field of network search, in particular to a work order search method, a work order search device and computing equipment.
Background
After a fault maintenance worker receives a maintenance work order, generally, search keywords are input according to the content of the work order, similar historical cases are searched, and a similar processing method is obtained, so that the fault processing efficiency is improved.
However, since the fault maintainers may come from different departments, which may cause differences in business understanding, it is not always possible to accurately summarize events described in the work order with a small number of search terms. Therefore, the current work order searching method has certain errors, so that the searching result is not accurate enough.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present invention provide a work order searching method, apparatus and computing device, which can improve the accuracy of a search result.
According to a first aspect of the embodiments of the present invention, a work order searching method is provided, including: receiving a recommendation request; acquiring a current work order according to the recommendation request; performing word segmentation on the current work order according to a preset word segmentation word bank to obtain a plurality of entries to be searched; determining the weight of each entry to be searched; sequencing all the entries to be searched according to the sequence of the weights of the entries to be searched from large to small; according to a preset query dictionary, sequentially searching the entries to be searched according to the sequence to obtain target work orders corresponding to the entries to be searched; and displaying the target work order according to the grade of the target work order.
In an optional manner, the determining the weight of each entry to be searched specifically includes: and setting weight, position and frequency of occurrence according to the word bank of the entry to be searched, and calculating the weight of the entry to be searched.
In an optional manner, the sequentially searching the to-be-searched terms according to the preset query dictionary and the sequence to obtain the target work order corresponding to the to-be-searched terms specifically includes: if the fact that the preset query dictionary has the query words identical to the entries to be searched is determined, acquiring a historical work order corresponding to the query words; and determining the historical work order corresponding to the query word as the target work order.
In an optional manner, the preset query dictionary includes a conflict linked list; the searching is sequentially performed on the entries to be searched according to the preset query dictionary and the sequence to obtain the target work orders corresponding to the entries to be searched, and the method specifically includes the following steps: calculating the hash value of the entry to be searched; acquiring a conflict linked list corresponding to the hash value of the entry to be searched in the preset query dictionary according to the hash value of the entry to be searched; and if the query word which is the same as the vocabulary entry to be searched exists in the conflict linked list corresponding to the hash value of the vocabulary entry to be searched, determining that the query word which is the same as the vocabulary entry to be searched exists in the preset query dictionary.
In an optional manner, the displaying the target work order according to the score of the target work order specifically includes: calculating the score of the historical work order corresponding to the query word; determining the score of the target work order according to the score of the historical work order corresponding to the query word; and displaying the target work order from large to small according to the grade of the target work order.
In an optional manner, the calculating a score of the historical work order corresponding to the query term specifically includes: calculating the score of the historical work order corresponding to the query term according to the following formula:
wherein, coord (q, d) is the number of hit query words t in the historical work order d, querynorm (q) is a preset query normalization parameter, tf (tind) is the frequency of the query words t in the historical work order d, idf (t) is the frequency of the query words t in all the historical work orders d corresponding to the query words, t.getboost () is a preset query weight parameter of the query words t, and norm (t, d) is a value obtained by squaring one of the total number of the words in the historical work order d.
In an optional manner, the method further comprises: and when the target work order is displayed, simultaneously displaying the current work order.
According to a second aspect of the embodiments of the present invention, there is provided a work order search apparatus including: the request receiving module is used for receiving a recommendation request; the current work order obtaining module is used for obtaining a current work order according to the recommendation request; the word segmentation module is used for segmenting the current work order according to a preset word segmentation word bank so as to obtain a plurality of entries to be searched; the weight determining module is used for determining the weight of each entry to be searched; the sorting module is used for sorting all the entries to be searched according to the sequence of the weights of the entries to be searched from large to small; the searching module is used for sequentially searching the entries to be searched according to the preset query dictionary and the sequence to acquire target work orders corresponding to the entries to be searched; and the display module is used for displaying the target work order according to the grade of the target work order.
According to a third aspect of embodiments of the present invention, there is provided a computing device comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus; the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation of the work order searching method.
According to a fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, in which at least one executable instruction is stored, and when the executable instruction is executed on a computing device, the computing device executes the method for searching the work order.
According to the embodiment of the invention, all the entries to be searched are sequenced according to the sequence of the weights of the entries to be searched from large to small, the entry which can describe the content of the current work order can be placed in front of the search engine, the entries to be searched are sequentially searched according to the sequence, the target work order is displayed according to the grade of the target work order corresponding to the entry to be searched, the historical work order which is most similar to the current work order can be recommended to the user, and therefore, the accuracy of the search result can be improved.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a work order searching method according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a correspondence relationship between a hash table entry and a conflict linked list according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a correspondence relationship between a query term and a posting list according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a work order searching apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein.
Because fault maintainers cannot accurately summarize events described in a work order by a small number of search keywords, the current work order search method has certain errors, so that the search result is not accurate enough.
Based on this, the embodiment of the invention provides a work order searching method and system, which can improve the accuracy of the search result.
Specifically, the embodiments of the present invention will be further explained below with reference to the drawings.
It should be understood that the following examples are provided by way of illustration and are not intended to limit the invention in any way to the particular embodiment disclosed.
Fig. 1 shows a flowchart of a work order searching method provided by an embodiment of the present invention. The method may be applied to a computing device. As shown in fig. 1, the method includes:
The recommendation request is a request which is triggered by a user on a work order processing interface and is used for inquiring a historical work order similar to the current work order.
And step 120, acquiring the current work order according to the recommendation request.
The current work order is a work order currently being processed or being prepared for processing. The current work order may include text documents such as documents, forms, and attachments, among others.
And step 130, segmenting the words of the current work order according to a preset word segmentation word bank to obtain a plurality of entries to be searched.
The preset word segmentation word bank can comprise a preset standard word bank and a preset professional word bank. The preset standard word stock comprises a plurality of common and commonly used words, and the preset professional word stock comprises a plurality of phrases or words used in the professional field. The preset professional word bank can be customized according to the requirements of users, and hot words of some search engines can be added. The word or phrase may be weighted in the predetermined standard word stock and the predetermined professional word stock, for example, a higher weight may be set for some specific words, or a higher weight may be set for some words with higher search heat.
In step 130, performing word segmentation on the current work order according to a preset word segmentation word bank to obtain a plurality of entries to be searched, which may specifically be: performing word segmentation on the current work order according to a preset professional word bank; performing word segmentation again on the residual content after word segmentation of the current work order according to a preset standard word bank; and taking the entry obtained by twice word segmentation as the entry to be searched. And taking phrases or words obtained by word segmentation of the current work order as entries to be searched. For example, if the current work order includes "5G network capability is open," 5G network is found in the preset professional lexicon, "capability" and "open" are found in the preset professional lexicon, the current work order is segmented into "5G network," capability "and" open, "and the entry to be searched is" 5G network, "" capability "and" open.
And step 140, determining the weight of each entry to be searched.
The weight of the entry to be searched is the weight of the phrase or word obtained by dividing the current work order into words. In step 140, determining the weight of each entry to be searched may specifically include: and setting weight, position and frequency of occurrence according to the word bank of the entry to be searched, and calculating the weight of the entry to be searched. The word stock setting weight refers to weight set in a preset standard word stock or a preset professional word stock; the position refers to the position of the entry to be searched in the current work order, for example, the weight of the word in the title is set to be greater than that of the word in the processing content; the occurrence frequency refers to the number of times that the entry to be searched appears in the current work order, for example, the weight of the word with a large number of occurrences is set to be large. For example, the term to be searched includes "5G network", "capability", "open", "5G network" existing in the title and content of the current work order, the number of occurrences is 10, the location weight of the "5G network" is 1, the frequency weight is 1, "ability" and "open" exist in the content of the current work order, "ability" appears 5 times, "open" appears 3 times, then the location weight of "capability" is 0.5 and the frequency weight is 0.5, the location weight of "open" is 0.5 and the frequency weight is 0.3, the weight of the "5G network" is set to 0.8 for the thesaurus, the weight of the "ability" thesaurus is set to 0.5, the weight of the "open" thesaurus is set to 0.5, the weight of the "5G network" is then 0.8 x 1 x 0.8, the weight of the "capacity" is 0.5 x 0.125, and the weight of the "open" is 0.5 x 0.3 x 0.075.
And 150, sequencing all the entries to be searched according to the sequence of the weights of the entries to be searched from large to small.
And after the weights of all the entries to be searched are obtained through calculation, all the entries to be searched are sequenced according to the weights of the entries to be searched and the sequence from big to small. The sorted entries to be searched can be used as a list to be searched. Through the mode, the entry which can most present the content of the current work order can be placed at the forefront.
And 160, searching the terms to be searched in sequence according to a preset query dictionary to obtain a target work order corresponding to the terms to be searched.
The preset query dictionary is used for maintaining relevant information of all words appearing in the historical work order set and recording position information of the inverted list corresponding to a certain word in the inverted work order file, so that when the preset query dictionary is used for searching, the inverted list of the words to be searched can be queried in the preset query dictionary.
The preset query dictionary may include a hash table and a reverse arrangement table. Each hash table item stores a pointer, the pointer points to a conflict linked list, and in the conflict linked list, words with the same hash value form a linked list structure. Since two different words obtain the same hash value, which is called a collision in the hash algorithm, the words with the same hash value are stored in the linked list. For example, as shown in fig. 2, fig. 2 shows the correspondence between the hash table entry and the conflict linked list. Each word corresponds to a posting list, which may include an identification of several historical work orders. For example, word 1 corresponds to a posting list of: historical work order 1, historical work order 2, historical work order 3, the list of falling arrangement that word 2 corresponds is: the list of the inverted arrangement corresponding to the historical worksheet 1 and the word 3 is as follows: historical work order 1, historical work order 3.
Wherein, prior to step 160, the method further comprises: and generating and updating a preset inquiry dictionary according to the historical work order. The method specifically comprises the following steps: the method comprises the steps of segmenting words of a historical work order according to a preset word segmentation dictionary, calculating a hash value of a word or a phrase through a hash function for a certain word or phrase in the historical work order, reading a pointer stored in the hash table according to the hash table corresponding to the hash value, obtaining a corresponding conflict linked list, if the same word or phrase exists in the conflict linked list, namely the word or phrase appears in the historical work order analyzed before, adding the historical work order into a reverse arrangement list of the word or the phrase, and if the same word or phrase does not exist in the conflict linked list, namely the word or the phrase appears for the first time, adding the word or the phrase into the conflict linked list, and adding the historical work order into the reverse arrangement list of the word or the phrase; performing the same operation on all historical work orders to generate a preset query dictionary; meanwhile, the newly appeared historical work order is processed in a timing mode, and then the preset inquiry dictionary is updated.
Wherein step 160 may comprise:
and 161, if the preset query dictionary is determined to have the query words identical to the entries to be searched, acquiring the historical work order corresponding to the query words, and determining the historical work order corresponding to the query words as the target work order.
In some embodiments, since the term to be searched may be a word or a phrase, when the term to be searched is a phrase, the preset query dictionary may not have the query word that is the same as the term to be searched, and the term to be searched needs to be segmented and then queried. Step 160 may also include:
and step 162, if the preset query dictionary is determined to have no query words which are the same as the vocabulary entry to be searched, segmenting the vocabulary entry to be searched according to a preset standard word bank.
And 163, if the preset query dictionary is determined to have the query words identical to the segmentation words of the entry to be searched, acquiring the historical work order corresponding to the query words, and determining the historical work order corresponding to the query words as the target work order.
In some embodiments, step 160 may further include:
and 164, if the preset query dictionary is determined not to have the query words same as the vocabulary entry to be searched, determining the similar meaning words of the vocabulary entry to be searched according to the preset similar meaning word bank.
And 165, if the fact that the preset query dictionary has the query words identical to the similar meaning words of the entry to be searched is determined, acquiring the historical work order corresponding to the query words, and determining the historical work order corresponding to the query words as the target work order.
In some embodiments, step 160 may further include:
and 166, if the fact that the preset query dictionary has the query words same as the vocabulary entry to be searched is determined, acquiring the historical work orders corresponding to the query words, segmenting the vocabulary entry to be searched according to a preset standard word bank, acquiring the historical work orders corresponding to the segmentation words of the vocabulary entry to be searched, determining the synonym words of the vocabulary entry to be searched according to a preset synonym word bank, acquiring the historical work orders corresponding to the synonym words of the vocabulary entry to be searched, and determining all the acquired historical work orders as the target work orders.
Specifically, determining whether a query word identical to the entry to be searched (or a participle of the entry to be searched or a near-sense word of the word to be searched) exists in the preset query dictionary may specifically include: calculating the hash value of the entry to be searched (or the participle of the entry to be searched or the similar meaning word of the word to be searched); acquiring a conflict linked list corresponding to the hash value of the entry to be searched (or the participle of the entry to be searched or the near-meaning word of the word to be searched) in a preset query dictionary according to the hash value of the entry to be searched (or the participle of the entry to be searched or the near-meaning word of the word to be searched); if the query word which is the same as the entry to be searched (or the participle of the entry to be searched or the near-meaning word of the word to be searched) exists in the conflict linked list corresponding to the hash value of the entry to be searched (or the participle of the entry to be searched or the near-meaning word of the word to be searched), determining that the query word which is the same as the entry to be searched (or the participle of the entry to be searched or the near-meaning word of the word to be searched) exists in the preset query dictionary.
The hash value of the entry to be searched (or the participle of the entry to be searched or the similar meaning word of the word to be searched) can be calculated through the hash function. After the hash value of the entry to be searched (or the segmentation of the entry to be searched or the similar meaning word of the word to be searched) is obtained through calculation, the hash table entry corresponding to the hash value is determined, so as to obtain the conflict chain table corresponding to the determined hash table entry. For example, referring to fig. 2, if the entry to be searched is "edirly", after the hash value of the entry to be searched is obtained through calculation, it is determined that the hash value corresponds to the number 4 slot, and then the conflict chain table corresponding to the number 4 slot is obtained. The query term refers to a term that exists in the conflict linked list. For example, referring to fig. 2, if the entry to be searched is "Ederly," the query word "Ederly" identical to the entry to be searched is found in the conflict chain table corresponding to the hash value of the entry to be searched, and then the historical work order corresponding to the query word "Ederly" is obtained.
And determining all historical work orders as target work orders if the historical work orders obtained after word segmentation of the entry to be searched are historical work orders corresponding to a plurality of query words. For example, as shown in fig. 3, the participles of the entry to be searched include word 1, word 2, word 3, and word 4, and all the historical worksheets corresponding to word 1, word 2, word 3, and word 4 are determined as the target worksheets.
And 170, displaying the target work order according to the grade of the target work order.
Wherein, step 170 specifically comprises: calculating the score of the historical work order corresponding to the query word; determining the score of the target work order according to the score of the historical work order corresponding to the query word; and displaying the target work order from large to small according to the grade of the target work order. By displaying the high-grade target work order in front, the user can conveniently search the most suitable work order.
The score of the historical work order corresponding to the query term can be calculated according to the following formula:
wherein, coord (q, d) is a scoring factor, which is the number of hit query words t in the historical work order d, querynorm (q) is a preset query normalization parameter, tf (tind) is the frequency of the query words t in the historical work order d, idf (t) is the frequency of the query words t in all the historical work orders d corresponding to the query words, t.getscore () is a preset query weight parameter of the query words t, and norm (t, d) is a value obtained by squaring one of the total number of the words in the historical work order d.
Wherein, coord (q, d) is a scoring factor and is based on the number of query words t appearing in the historical work order d. The more query terms t are in one historical work order d, which indicates that the higher the matching degree of the historical work order d is, the higher the score of the historical work order d is, and can be obtained by the following formula:
coord(q,d)＝overlap/maxOverlay
wherein, overlap is the number of hit searches (no calculation of hit repeat) in the title or content of the document, and maxooverlay is the number of search conditions, i.e. the number after word segmentation. For example, if the entry to be searched is "test mobile high definition", the participle of the entry to be searched is "test mobile high definition", if the title of the historical work order d1 includes "test", and the content of the historical work order d1 includes "test mobile", the coord (q, d) of the historical work order d1 is 2/3; if the title of the historical work order d2 includes "test" and the contents of the historical work order d1 includes "step", then the coord (q, d) of the historical work order d2 is 1/3.
Wherein, querynorm (q) is a preset query normalization parameter, which can be preset. querynorm (q) is used to calculate the sum of variances for each query entry. querynorm (q) does not affect the ranking results, but only allows comparison between different scores.
Wherein tf (tind) is the frequency of the query term t appearing in the historical work order d. If the occurrence frequency of the query word t in the historical work order d is more, the score of the historical work order d is higher, and the score can be obtained through the following formula:
where a is the number of times a search term appears in a document. For example, if the query term is "test", and the number of occurrences of "test" in the historical work order d1 is 2, then tf (tind) of the historical work order d1 is
Wherein idf (t) is the frequency of the query term t and all historical work orders d corresponding to the query term, and can be obtained by the following formula:
where numDocs is the total number of all documents and docFreq is the number of documents in which the search term appears. The smaller the docFreq, the larger the idf (t). For example, if the query word is "test", the total number of all historical work orders is 1000, where the number of historical work orders whose title includes "test" is 100, then idf (t) ≈ 1+ log (1000/(100+1)) ≈ 1+ log (1000/100) ≈ 1+ log (10) ≈ 1+1 ═ 2. When a plurality of query terms exist, respectively calculating idf (t) of the query terms, and then multiplying the idf (t) of all the query terms to obtain the total idf (t).
Wherein, t.getboost () is a preset query weight parameter of the query word t, and can be set according to the needs of the user or preset by the system. For example, a higher preset query weight parameter is set for the entry to be searched, and a lower preset query weight parameter is set for the segmentation of the entry to be searched and the similar meaning of the entry to be searched. For another example, the host is host ^10.0OR itemDesc, the weight of host in itemName is specified to be 10.0, and the weight of itemDesc is 1.
Where norm (t, d) is a weighting of the length and is used to precede the comparison for documents that match the same. For example, historical work order d 1: test, historical work order d 2: a testing step, namely when the query word is "test", d1 and d2 are both matched, and d1 is placed in front of d2, because d1 is more consistent with a complete match, which can be obtained by the following formula:
norm(t,d)＝doc.getBoost()·lengthNorm·∏f.getBoost()
wherein doc, getboost represents the weight of the document, f, getboost represents the weight of the field, and if doc, getboost and f, getboost are both set to 1, norm (t, d) is length norm. Wherein,
term is a Term in the document, which is the smallest unit of search, and numTerms is the total number of terms in the document. The larger the total number of Term, the longer the document, the smaller the norm (t, d), and the smaller the total number of Term, the shorter the document, the larger the norm (t, d). For example, historical work order d 2: a testing step, if the query word t is 'test', the norm (t, d) of the historical work order d2 is
According to the embodiment of the invention, all the entries to be searched are sequenced according to the sequence of the weights of the entries to be searched from large to small, the entry which can describe the content of the current work order can be placed in front of the search engine, the entries to be searched are sequentially searched according to the sequence, the target work order is displayed according to the grade of the target work order corresponding to the entry to be searched, the historical work order which is most similar to the current work order can be recommended to the user, and therefore, the accuracy of the search result can be improved.
In some examples, the method further comprises:
and 180, displaying the current work order when the target work order is displayed.
The target work order obtained after searching and the current work order coexist, so that a user can look up cases when processing the current work order, the user is prevented from switching to other function pages to perform case recommendation operation, and user experience is improved.
Fig. 4 shows a schematic structural diagram of a work order searching apparatus provided in an embodiment of the present invention. The apparatus may be applied to a computing device. As shown in fig. 4, the apparatus 200 includes: a request receiving module 210, a current work order obtaining module 220, a word segmentation module 230, a weight determination module 240, a ranking module 250, a search module 260, and a display module 270.
The request receiving module 210 is configured to receive a recommendation request; the current work order obtaining module 220 is configured to obtain a current work order according to the recommendation request; the word segmentation module 230 is configured to perform word segmentation on the current work order according to a preset word segmentation word bank to obtain a plurality of entries to be searched; the weight determining module 240 is configured to determine a weight of each entry to be searched; the sorting module 250 is configured to sort all the entries to be searched according to the order of the weights of the entries to be searched from large to small; the searching module 260 is configured to sequentially search the entries to be searched according to the preset query dictionary and the sequence, so as to obtain a target work order corresponding to the entries to be searched; the display module 270 is configured to display the target work order according to the score of the target work order.
In an optional manner, the weight determining module 240 is specifically configured to: and setting weight, position and frequency of occurrence according to the word bank of the entry to be searched, and calculating the weight of the entry to be searched.
In an optional manner, the search module 260 is specifically configured to: if the fact that the preset query dictionary has the query words identical to the entries to be searched is determined, acquiring a historical work order corresponding to the query words; and determining the historical work order corresponding to the query word as the target work order.
In an optional manner, the preset query dictionary includes a conflict linked list; the search module 260 is further specifically configured to: calculating the hash value of the entry to be searched; acquiring a conflict linked list corresponding to the hash value of the entry to be searched in the preset query dictionary according to the hash value of the entry to be searched; and if the query word which is the same as the vocabulary entry to be searched exists in the conflict linked list corresponding to the hash value of the vocabulary entry to be searched, determining that the query word which is the same as the vocabulary entry to be searched exists in the preset query dictionary.
In an optional manner, the display module 270 is specifically configured to: calculating the score of the historical work order corresponding to the query word; determining the score of the target work order according to the score of the historical work order corresponding to the query word; and displaying the target work order from large to small according to the grade of the target work order.
In an optional manner, the display module 270 is specifically configured to: calculating the score of the historical work order corresponding to the query term according to the following formula:
wherein, coord (q, d) is the number of hit query words t in the historical work order d, querynorm (q) is a preset query normalization parameter, tf (tind) is the frequency of the query words t in the historical work order d, idf (t) is the frequency of the query words t in all the historical work orders d corresponding to the query words, t.getboost () is a preset query weight parameter of the query words t, and norm (t, d) is a value obtained by squaring one of the total number of the words in the historical work order d.
In an alternative manner, the display module 270 is further configured to: and when the target work order is displayed, simultaneously displaying the current work order.
It should be noted that, the work order search apparatus provided in the embodiments of the present invention is an apparatus capable of executing the work order search method, and all embodiments of the work order search method are applicable to the apparatus and can achieve the same or similar beneficial effects.
According to the embodiment of the invention, all the entries to be searched are sequenced according to the sequence of the weights of the entries to be searched from large to small, the entry which can describe the content of the current work order can be placed in front of the search engine, the entries to be searched are sequentially searched according to the sequence, the target work order is displayed according to the grade of the target work order corresponding to the entry to be searched, the historical work order which is most similar to the current work order can be recommended to the user, and therefore, the accuracy of the search result can be improved.
Fig. 5 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 5, the computing device may include: a processor (processor)302, a communication Interface 304, a memory 306, and a communication bus 308.
Wherein: the processor 302, communication interface 304, and memory 306 communicate with each other via a communication bus 308. A communication interface 304 for communicating with network elements of other devices, such as clients or other servers. The processor 302 is configured to execute the program 310, and may specifically execute the relevant steps in the embodiment of the work order search method described above.
In particular, program 310 may include program code comprising computer-executable instructions.
The processor 302 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the present invention. The content delivery network includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 306 for storing a program 310. Memory 306 may comprise high-speed RAM memory and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 310 may be specifically invoked by the processor 302 to cause the computing device to perform the operations in the work order search method in the above-described embodiments.
According to the embodiment of the invention, all the entries to be searched are sequenced according to the sequence of the weights of the entries to be searched from large to small, the entry which can describe the content of the current work order can be placed in front of the search engine, the entries to be searched are sequentially searched according to the sequence, the target work order is displayed according to the grade of the target work order corresponding to the entry to be searched, the historical work order which is most similar to the current work order can be recommended to the user, and therefore, the accuracy of the search result can be improved.
An embodiment of the present invention provides a computer-readable storage medium, where the storage medium stores at least one executable instruction, and when the executable instruction is executed on a computing device, the computing device is enabled to execute a work order searching method in any method embodiment described above. The executable instructions may be specifically configured to cause the computing device to perform the operations in the work order search method in the foregoing embodiments.
According to the embodiment of the invention, all the entries to be searched are sequenced according to the sequence of the weights of the entries to be searched from large to small, the entry which can describe the content of the current work order can be placed in front of the search engine, the entries to be searched are sequentially searched according to the sequence, the target work order is displayed according to the grade of the target work order corresponding to the entry to be searched, the historical work order which is most similar to the current work order can be recommended to the user, and therefore, the accuracy of the search result can be improved.
The embodiment of the invention provides a work order searching device which is used for executing the work order searching method.
Embodiments of the present invention provide a computer program, where the computer program can be called by a processor to enable a computing device to execute a work order search method in any of the above method embodiments.
Embodiments of the present invention provide a computer program product comprising a computer program stored on a computer-readable storage medium, the computer program comprising program instructions that, when run on a computer, cause the computer to perform the work order searching method in any of the above-mentioned method embodiments.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A work order search method is characterized by comprising the following steps:
receiving a recommendation request;
acquiring a current work order according to the recommendation request;
performing word segmentation on the current work order according to a preset word segmentation word bank to obtain a plurality of entries to be searched;
determining the weight of each entry to be searched;
sequencing all the entries to be searched according to the sequence of the weights of the entries to be searched from large to small;
according to a preset query dictionary, sequentially searching the entries to be searched according to the sequence to obtain target work orders corresponding to the entries to be searched;
and displaying the target work order according to the grade of the target work order.
2. The method according to claim 1, wherein the determining the weight of each entry to be searched specifically comprises:
and setting weight, position and frequency of occurrence according to the word bank of the entry to be searched, and calculating the weight of the entry to be searched.
3. The method according to claim 1, wherein the sequentially searching the to-be-searched terms according to the preset query dictionary in the order to obtain the target work order corresponding to the to-be-searched terms specifically comprises:
if the fact that the preset query dictionary has the query words identical to the entries to be searched is determined, acquiring a historical work order corresponding to the query words;
and determining the historical work order corresponding to the query word as the target work order.
4. The method of claim 3, wherein the predetermined query dictionary comprises a conflict linked list;
the searching is sequentially performed on the entries to be searched according to the preset query dictionary and the sequence to obtain the target work orders corresponding to the entries to be searched, and the method specifically includes the following steps:
calculating the hash value of the entry to be searched;
acquiring a conflict linked list corresponding to the hash value of the entry to be searched in the preset query dictionary according to the hash value of the entry to be searched;
and if the query word which is the same as the vocabulary entry to be searched exists in the conflict linked list corresponding to the hash value of the vocabulary entry to be searched, determining that the query word which is the same as the vocabulary entry to be searched exists in the preset query dictionary.
5. The method according to claim 3, wherein the displaying the target work order according to the score of the target work order specifically comprises:
calculating the score of the historical work order corresponding to the query word;
determining the score of the target work order according to the score of the historical work order corresponding to the query word;
and displaying the target work order from large to small according to the grade of the target work order.
6. The method according to claim 5, wherein the calculating the score of the historical work order corresponding to the query term specifically comprises:
calculating the score of the historical work order corresponding to the query term according to the following formula:
wherein, coord (q, d) is the number of hit query words t in the historical work order d, querynorm (q) is a preset query normalization parameter, tf (tind) is the frequency of the query words t in the historical work order d, idf (t) is the frequency of the query words t in all the historical work orders d corresponding to the query words, t.getboost () is a preset query weight parameter of the query words t, and norm (t, d) is a value obtained by squaring one of the total number of the words in the historical work order d.
7. The method according to any one of claims 1-6, further comprising:
and when the target work order is displayed, simultaneously displaying the current work order.
8. A work order search apparatus, comprising:
the request receiving module is used for receiving a recommendation request;
the current work order obtaining module is used for obtaining a current work order according to the recommendation request;
the word segmentation module is used for segmenting the current work order according to a preset word segmentation word bank so as to obtain a plurality of entries to be searched;
the weight determining module is used for determining the weight of each entry to be searched;
the sorting module is used for sorting all the entries to be searched according to the sequence of the weights of the entries to be searched from large to small;
the searching module is used for sequentially searching the entries to be searched according to the preset query dictionary and the sequence to acquire target work orders corresponding to the entries to be searched;
and the display module is used for displaying the target work order according to the grade of the target work order.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the work order search method of any of claims 1-7.
10. A computer-readable storage medium having stored therein at least one executable instruction that, when executed on a computing device, causes the computing device to perform operations of the work order search method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010269941.0A CN113495947B (en) | 2020-04-08 | 2020-04-08 | Work order searching method and device and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010269941.0A CN113495947B (en) | 2020-04-08 | 2020-04-08 | Work order searching method and device and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113495947A true CN113495947A (en) | 2021-10-12 |
| CN113495947B CN113495947B (en) | 2024-05-10 |
Family
ID=77995633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010269941.0A Active CN113495947B (en) | 2020-04-08 | 2020-04-08 | Work order searching method and device and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113495947B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982153A (en) * | 2012-11-29 | 2013-03-20 | 北京亿赞普网络技术有限公司 | Information retrieval method and device |
| US20170178145A1 (en) * | 2015-12-16 | 2017-06-22 | Bmc Software, Inc. | Using multi-factor context for resolving customer service issues |
| WO2017121251A1 (en) * | 2016-01-13 | 2017-07-20 | 北京三快在线科技有限公司 | Information push method and device |
| CN107798047A (en) * | 2017-07-26 | 2018-03-13 | 上海壹账通金融科技有限公司 | Repeat work order detection method, device, server and medium |
| CN108874995A (en) * | 2018-06-12 | 2018-11-23 | 广东电网有限责任公司 | Method and device for establishing customer service database and electronic equipment |
| CN109241259A (en) * | 2018-08-24 | 2019-01-18 | 国网江苏省电力有限公司苏州供电分公司 | Natural language querying method, apparatus and system based on ER model |
| CN109948036A (en) * | 2017-11-15 | 2019-06-28 | 腾讯科技（深圳）有限公司 | A kind of calculation method and device segmenting lexical item weight |
| CN110222203A (en) * | 2019-06-19 | 2019-09-10 | 深圳前海微众银行股份有限公司 | Metadata searching method, device, equipment and computer readable storage medium |
| CN110826735A (en) * | 2019-10-31 | 2020-02-21 | 上海玖道信息科技股份有限公司 | Electric power SCADA intelligent multidimensional query and maintenance method |
| US20200097599A1 (en) * | 2018-09-21 | 2020-03-26 | International Business Machines Corporation | Weighting of unobserved terms in a language model for information retrieval using lexical resources |
-
2020
- 2020-04-08 CN CN202010269941.0A patent/CN113495947B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982153A (en) * | 2012-11-29 | 2013-03-20 | 北京亿赞普网络技术有限公司 | Information retrieval method and device |
| US20170178145A1 (en) * | 2015-12-16 | 2017-06-22 | Bmc Software, Inc. | Using multi-factor context for resolving customer service issues |
| WO2017121251A1 (en) * | 2016-01-13 | 2017-07-20 | 北京三快在线科技有限公司 | Information push method and device |
| CN107798047A (en) * | 2017-07-26 | 2018-03-13 | 上海壹账通金融科技有限公司 | Repeat work order detection method, device, server and medium |
| CN109948036A (en) * | 2017-11-15 | 2019-06-28 | 腾讯科技（深圳）有限公司 | A kind of calculation method and device segmenting lexical item weight |
| CN108874995A (en) * | 2018-06-12 | 2018-11-23 | 广东电网有限责任公司 | Method and device for establishing customer service database and electronic equipment |
| CN109241259A (en) * | 2018-08-24 | 2019-01-18 | 国网江苏省电力有限公司苏州供电分公司 | Natural language querying method, apparatus and system based on ER model |
| US20200097599A1 (en) * | 2018-09-21 | 2020-03-26 | International Business Machines Corporation | Weighting of unobserved terms in a language model for information retrieval using lexical resources |
| CN110222203A (en) * | 2019-06-19 | 2019-09-10 | 深圳前海微众银行股份有限公司 | Metadata searching method, device, equipment and computer readable storage medium |
| CN110826735A (en) * | 2019-10-31 | 2020-02-21 | 上海玖道信息科技股份有限公司 | Electric power SCADA intelligent multidimensional query and maintenance method |
Non-Patent Citations (1)
| Title |
|---|
| 吴刚勇 等: ""基于自然语言处理技术的电力客户投诉工单文本挖掘分析"", 《中国设备工程》, 10 September 2018 (2018-09-10), pages 154 - 156 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113495947B (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019091026A1 (en) | Knowledge base document rapid search method, application server, and computer readable storage medium | |
| US11449767B2 (en) | Method of building a sorting model, and application method and apparatus based on the model | |
| US8606778B1 (en) | Document ranking based on semantic distance between terms in a document | |
| JP4809441B2 (en) | Estimating search category synonyms from user logs | |
| JP5379696B2 (en) | Information retrieval system, method and software with concept-based retrieval and ranking | |
| US8037078B2 (en) | Corpus clustering, confidence refinement, and ranking for geographic text search and information retrieval | |
| CN105653562B (en) | The calculation method and device of correlation between a kind of content of text and inquiry request | |
| US20030225763A1 (en) | Self-improving system and method for classifying pages on the world wide web | |
| US8510312B1 (en) | Automatic metadata identification | |
| CN107357777B (en) | Method and device for extracting label information | |
| US9292509B2 (en) | Supplementing search results with information of interest | |
| CN110968789B (en) | Electronic book pushing method, electronic equipment and computer storage medium | |
| CN107870915B (en) | Indication of search results | |
| US6278990B1 (en) | Sort system for text retrieval | |
| CN109522275B (en) | Label mining method based on user production content, electronic device and storage medium | |
| CN113779364A (en) | Searching method based on label extraction and related equipment thereof | |
| CN113495947B (en) | Work order searching method and device and computing equipment | |
| JP2003208447A (en) | Device, method and program for retrieving document, and medium recorded with program for retrieving document | |
| CN111221943A (en) | Query result matching degree calculation method and device | |
| CN115905577B (en) | Knowledge graph construction method and device and rule retrieval method and device | |
| CN113177061A (en) | Searching method and device and electronic equipment | |
| CN113468339A (en) | Label extraction method, system, electronic device and medium based on knowledge graph | |
| US9087119B2 (en) | Method for searching in a plurality of data sets and search engine | |
| US20130091166A1 (en) | Method and apparatus for indexing information using an extended lexicon | |
| CN111930928B (en) | Text retrieval result scoring method, retrieval method and device |
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 |