CN117194801B - Public service transferring system and method based on technology - Google Patents
Public service transferring system and method based on technology Download PDFInfo
- Publication number
- CN117194801B CN117194801B CN202311463708.6A CN202311463708A CN117194801B CN 117194801 B CN117194801 B CN 117194801B CN 202311463708 A CN202311463708 A CN 202311463708A CN 117194801 B CN117194801 B CN 117194801B
- Authority
- CN
- China
- Prior art keywords
- search
- text
- user
- historical
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 32
- 238000012546 transfer Methods 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 6
- 230000007547 defect Effects 0.000 abstract description 8
- 230000006399 behavior Effects 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical transfer public service field and provides a technical transfer public service system and a technical transfer public service method, wherein the system comprises a public service center, an analysis module, a search module, an acquisition module, a similarity calculation module and a text collection module; the public service center is respectively connected with the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module and is used for managing the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module. According to the technology-based public service system, through the identity information and the search text data set of the current search user, all final target search text data sets of the current search user are searched, accuracy of search recommendation results is improved, and the defect that the accuracy of generated search recommendation results is low when related categories are not searched before or user behaviors are less is overcome.
Description
Technical Field
The application relates to the technical transfer public service field, in particular to a technical transfer public service system and method.
Background
With the development of technology transfer platforms becoming more and more mature, the number of users increases, and the technical directions stored therein increase, so that the number of terms that can be selected or referenced is undoubtedly excessive, and the required technical data cannot be found quickly when the users search, so that a more intelligent search mode is necessary to increase the use experience and search efficiency of the users. The existing search mode mainly generates search recommendation results according to the past search records of users. The above method does in many cases work well. However, the above method does not work for improving accuracy of search recommendation results for categories that the user has not searched or when the user has less behavior.
Disclosure of Invention
The embodiment of the application provides a public service system and a public service method based on technology transfer, which aim to improve the accuracy of search recommendation results and overcome the defect of low accuracy of generated search recommendation results when a user does not search related categories before or the user acts less.
In a first aspect, an embodiment of the present application provides a technology-based public service transfer system, including a public service center, an parsing module, a searching module, an obtaining module, a similarity calculating module, and a text collecting module; the public service center is respectively connected with the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module and is used for managing the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module;
The analysis module is used for: analyzing the search operation service initiated by the user terminal to obtain a search task; the search task carries the identity information, the search keywords and the search quantity of the current search user; the current searching user is a user operating the user terminal;
the search module is used for: searching a first search text data set according to the search keyword and the search quantity;
the acquisition module is used for: acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set;
the similarity calculation module is used for: determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set;
the text collection module is used for: and collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user.
In a second aspect, an embodiment of the present application provides a technology-based public service transfer method, which is applied to the technology-based public service transfer system in the first aspect, and includes:
Analyzing the search operation service initiated by the user terminal to obtain a search task; the search task carries the identity information, the search keywords and the search quantity of the current search user; the current searching user is a user operating the user terminal;
searching a first search text data set according to the search keyword and the search quantity;
acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set;
determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set;
and collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user.
In one embodiment, the identity information includes age information, gender information, education level information, and user social information;
the step of searching the user set according to the identity information acquisition target history comprises the following steps:
determining a first historical search user set associated with the current search user according to the age information, the gender information and the education level information;
And determining a second historical searching user set in the first historical searching user set according to the user social information, and determining the second historical searching user set as the target historical searching user set.
In one embodiment, the determining a first set of historical search users associated with the current search user according to the age information, the gender information, and the education level information includes:
calculating the age difference value between each historical searching user and the current searching user according to the age information;
determining the gender correlation coefficient of each historical searching user and the current searching user according to the gender information; the sex correlation coefficient of the same sex is 1, and the sex correlation coefficient of different sexes is 0.5;
determining a cultural difference degree coefficient of each historical searching user and the current searching user according to the education degree information;
calculating a relevancy coefficient according to the age difference value, the gender relevancy coefficient and the cultural difference degree coefficient of each historical searching user and the current searching user;
determining the first historical search user set according to the relevance coefficient of each historical search user and the current search user;
The calculation formula of the association coefficient is as follows:wherein G is a relevance coefficient, A g For age difference, V g For the sex correlation coefficient, C g Is a cultural difference degree coefficient.
In one embodiment, the determining a second historical search user set of the first historical search user set according to the user social information includes:
determining a social relation tree of each user in the current searching user and the first historical searching user set according to the user social information; the social relation tree comprises a single-path tree and a multi-path tree;
if the social relation tree is determined to be a single-path tree, determining all users with the path length of the social relation tree being more than 5 in the first historical searching user set as the second historical searching user set; or alternatively, the first and second heat exchangers may be,
and if the social relation tree is determined to be a multi-path tree, determining all users including 3-level leaf nodes in the social relation tree in the first historical searching user set as the second historical searching user set.
In one embodiment, the determining a third set of search text data based on the text semantic similarity of the first set of search text data and the second set of search text data includes:
Acquiring a first text in the first search text data set and a second text in the second search text data set; the first text is located in any text in the first search text data set, and the second text is located in any text in the second search text data set;
calculating the text cosine similarity of the first text and the second text according to a pre-trained context model; the calculation formula of the text cosine similarity is as follows:wherein (1)>For text cosine similarity, P 1 For the first text, P 2 X is the second text i For P in the first text 1 The weight value of the ith word segment, y i For P in the second text 2 The weight value of the ith word segment in the list;
obtaining the similarity of any word segmentation of the first text and any word segmentation of the second text according to the pre-training context model so as to calculate the similarity of the text offset of the first text and the second text;
calculating the text semantic similarity of the first text and the second text according to the text cosine similarity and the text offset similarity of the first text and the second text;
and collecting all second texts with the text semantic similarity larger than or equal to a preset value to obtain the third search text data set.
In one embodiment, the obtaining the similarity of any word of the first text and any word of the second text according to the pre-trained context model to calculate the similarity of the text offsets of the first text and the second text includes: according to the first text P 1 The word segmentation result of the first text P is obtained 1 Length of (2)And word S i At the first text P 1 Relative position +.>；
According to the second text P 2 The word segmentation result of the second text P is obtained 2 Length of (2)And word segmentation W j At the second text P 2 Relative position +.>；
Acquiring segmentation S i Is (are) adjacent to each otherDegree of harmony->And acquire the segmentation word W j Is +.>Degree of harmony->；
Calculating the similarity according to formula (1)；
Wherein (1)>Representing word S i And word segmentation W j A common neighboring point;
calculating the first text P according to formula (2) 1 And the second text P 2 Text offset similarity of (c)；
Wherein m is the first text P 1 The total number of the medium segmentation words, n is the second text P 2 Total number of medium-sized words. In one embodiment, the text semantic similarity is calculated by the following formula: />Wherein S is text semantic similarity.
In a third aspect, embodiments of the present application provide a computer device, where the computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the technology-based transfer public service method of the second aspect when the computer program is executed.
In a fourth aspect, embodiments of the present application provide a non-transitory computer readable storage medium comprising a computer program that, when executed by a processor, implements the technology-based transfer public service method of the second aspect.
The system comprises a public service center, an analysis module, a search module, an acquisition module, a similarity calculation module and a text collection module; the public service center is respectively connected with the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module and is used for managing the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module.
In the process of transferring public service based on technology, through the identity information and the search text data set of the current search user, the final all target search text data sets of the current search user are searched, the accuracy of search recommendation results is improved, and the defect of low accuracy of generated search recommendation results when the user does not search related categories before or the user acts less is overcome.
Drawings
For a clearer description of the present application or of the prior art, the drawings that are used in the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description below are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a technology-based transfer public service system according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a technology-based public service transfer method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a technology-based transfer public service system according to an embodiment of the present application. The embodiment of the application provides a public service system based on technology transfer, which comprises a public service center, an analysis module, a search module, an acquisition module, a similarity calculation module and a text collection module; the public service center is respectively connected with the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module and is used for managing the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module;
when a text is required to be searched, a search task can be initiated to a public service system through a user terminal by using a search operation service. Thus, the public service system can respond to the search operation service initiated by the user terminal.
In an embodiment, a search operation service initiated by a user terminal is analyzed through an analysis module to obtain a search task, wherein the search task carries identity information, search keywords and search quantity of a current search user, and the current search user is a user operating the user terminal.
In one embodiment, the first set of search text data is searched by a search module based on the search keywords and the number of searches.
In one embodiment, a target historical search user set is acquired according to the identity information through an acquisition module, and a second search text data set of the target historical search user set is acquired.
In one embodiment, the third set of search text data is determined by a similarity calculation module based on the text semantic similarity of the first set of search text data and the second set of search text data.
In one embodiment, the first search text data set and the third search text data set are collected through a text collection module to obtain a target search text data set of the current search user.
The public service system based on technology transfer provided by the embodiment of the application comprises a public service center, an analysis module, a search module, an acquisition module, a similarity calculation module and a text collection module; the public service center is respectively connected with the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module and is used for managing the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module. In the process of transferring public service based on technology, through the identity information and the search text data set of the current search user, the final all target search text data sets of the current search user are searched, the accuracy of search recommendation results is improved, and the defect of low accuracy of generated search recommendation results when the user does not search related categories before or the user acts less is overcome.
The technology-based public service method provided by the embodiment of the present application is described below, and the technology-based public service method described below and the technology-based public service system described above may be referred to correspondingly.
Referring to fig. 2, fig. 2 is a schematic flow chart of a technology-based public service transfer method according to an embodiment of the present application.
The public service transferring method based on the technology provided by the embodiment of the application comprises the following steps:
step 201, analyzing a search operation service initiated by a user terminal to obtain a search task;
step 202, searching a first search text data set according to the search keywords and the search quantity;
step 203, acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set;
step 204, determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set;
and 205, collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user.
It should be noted that, the technology-based public service transfer method provided by the embodiment of the application is applied to a technology-based public service transfer system, and the technology-based public service transfer system includes a public service center, an analysis module, a search module, an acquisition module, a similarity calculation module and a text collection module; the public service center is respectively connected with the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module.
Specifically, when a text needs to be searched, a search task can be initiated to a public service system through a user terminal by using a search operation service. Thus, the public service system can respond to the search operation service initiated by the user terminal.
The public service system analyzes the search operation service initiated by the user terminal to obtain a search task, wherein the search task carries the identity information, the search keywords and the search quantity of the current search user, and the current search user is the user operating the user terminal.
Further, the public service system searches the first search text data set according to the search keyword and the search quantity.
Further, the public service system acquires a target historical search user set according to the identity information, and acquires a second search text data set of the target historical search user set.
Further, the public service system determines a third set of search text data based on the text semantic similarity of the first set of search text data and the second set of search text data.
Further, the public service system gathers the first search text data set and the third search text data set to obtain a target search text data set of the current search user.
According to the technical transfer public service method, the search operation service initiated by the user terminal is analyzed to obtain a search task; searching the first search text data set according to the search keywords and the search quantity; acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set; determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set; and collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user. In the process of transferring public service based on technology, through the identity information and the search text data set of the current search user, the final all target search text data sets of the current search user are searched, the accuracy of search recommendation results is improved, and the defect of low accuracy of generated search recommendation results when the user does not search related categories before or the user acts less is overcome.
In one embodiment, obtaining the target history search user set according to the identity information includes:
determining a first historical search user set associated with the current search user according to the age information, the gender information and the education level information;
and determining a second historical searching user set in the first historical searching user set according to the user social information, and determining the second historical searching user set as the target historical searching user set.
The identity information includes age information, gender information, education level information, and user social information, which may include professional information, activity range information, social circle information, and social relationship information.
Specifically, the public service system determines a first historical search user set associated with a current search user according to age information, gender information and education level information.
Further, the public service system determines a second historical search user set in the first historical search user set according to the user social information, and determines the second historical search user set as a target historical search user set.
According to the method and the device for searching the text data set, through the identity information and the text data set of the current searching user, all final target text data sets of the current searching user are searched, accuracy of the search recommendation result is improved, and the defect that the accuracy of the generated search recommendation result is low when the user does not search related categories before or the user acts less is overcome.
In one embodiment, determining a first set of historical search users associated with the current search user based on the age information, the gender information, and the education level information includes:
calculating the age difference value between each historical searching user and the current searching user according to the age information;
determining the gender correlation coefficient of each historical searching user and the current searching user according to the gender information; the sex correlation coefficient of the same sex is 1, and the sex correlation coefficient of different sexes is 0.5;
determining a cultural difference degree coefficient of each historical searching user and the current searching user according to the education degree information;
calculating a relevancy coefficient according to the age difference value, the gender relevancy coefficient and the cultural difference degree coefficient of each historical searching user and the current searching user;
Determining the first historical search user set according to the relevance coefficient of each historical search user and the current search user;
the calculation formula of the association coefficient is as follows:wherein G is a relevance coefficient, A g For age difference, V g For the sex correlation coefficient, C g Is a cultural difference degree coefficient.
Specifically, the public service system calculates an age difference value between each historical search user and the current search user according to the age information.
Further, the public service system determines a gender correlation coefficient of each historical search user and the current search user according to the gender information, wherein the gender correlation coefficient of the same gender is 1, and the gender correlation coefficients of different genders are 0.5.
Further, the public service system determines a cultural difference degree coefficient of each historical search user and the current search user according to the educational degree information, wherein the educational degree can comprise a primary educational degree, a junior middle school educational degree, a college educational degree and a research student educational degree, the cultural coefficient value of the primary educational degree is 0.5, the cultural coefficient value of the junior middle school educational degree is 1, the cultural coefficient value of the college educational degree is 2, and the cultural coefficient value of the research student educational degree is 4.
Further, the public service system calculates a relevance coefficient according to the age difference value, the gender relevance coefficient and the cultural difference degree coefficient of each historical search user and the current search user. Further, the public service system determines a first historical search user set according to the relevance coefficient of each historical search user and the current search user, wherein the calculation formula of the relevance coefficient is as follows:wherein G is a relevance coefficient, A g For age difference, V g For the sex correlation coefficient, C g Is a cultural difference degree coefficient.
According to the method and the device for searching the text data set of the target search through the identity information, accuracy of the recommended search results is improved, and the defect that the accuracy of the recommended search results is low when the user does not search related categories before or the user acts are few is overcome.
In an embodiment, determining a second historical search user set in the first historical search user set according to the user social information includes:
determining a social relation tree of each user in the current searching user and the first historical searching user set according to the user social information; the social relation tree comprises a single-path tree and a multi-path tree;
If the social relation tree is determined to be a single-path tree, determining all users with the path length of the social relation tree being more than 5 in the first historical searching user set as the second historical searching user set; or alternatively, the first and second heat exchangers may be,
and if the social relation tree is determined to be a multi-path tree, determining all users including 3-level leaf nodes in the social relation tree in the first historical searching user set as the second historical searching user set.
Specifically, the public service system determines a social relationship tree of each user in the current search user and the first historical search user set according to the user social information, wherein the social relationship tree comprises a single-path tree and a multi-path tree.
If the social relation tree is determined to be a single-path tree, the public service system determines all users with the path length of more than 5 in the first historical searching user set as a second historical searching user set. In one embodiment, user 1 has a social relationship tree of a-b-c-o and user 2 has a social relationship tree of a-c-e-d-f-r, thus determining user 2 as a user in the second set of historically searched users.
If the social relation tree is determined to be a multi-path tree, the public service system determines all users comprising 3-level leaf nodes in the social relation tree in the first historical searching user set as a second historical searching user set. In one embodiment, the social relationship tree of user 1 is a- { b- { e, f, g }, c, d }, that is, the a-root node has 3 primary leaf nodes a, b, c, and the b-node has 3 primary leaf nodes e, f, g. The social relationship tree for user 1 is a- { b- { e- { e, r, t }, f, g }, c, d }, thus determining user 2 as a user in the second set of historic search users.
In an embodiment, determining a third set of search text data based on text semantic similarity of the first set of search text data and the second set of search text data comprises:
acquiring a first text in the first search text data set and a second text in the second search text data set;
calculating the text cosine similarity of the first text and the second text according to a pre-trained context model; the calculation formula of the text cosine similarity is as follows:wherein (1)>For text cosine similarity, P 1 For the first text, P 2 Is the second oneText, X i For P in the first text 1 The weight value of the ith word segment, y i For P in the second text 2 The weight value of the ith word segment in the list;
obtaining the similarity of any word segmentation of the first text and any word segmentation of the second text according to the pre-training context model so as to calculate the similarity of the text offset of the first text and the second text;
calculating the text semantic similarity of the first text and the second text according to the text cosine similarity and the text offset similarity of the first text and the second text;
and collecting all second texts with the text semantic similarity larger than or equal to a preset value to obtain the third search text data set.
Specifically, the public service system obtains a first text in the first search text data set and a second text in the second search text data set, wherein the first text is located in any text in the first search text data set, and the second Wen Benwei is located in any text in the second search text data set.
Further, the public service system calculates the text cosine similarity of the first text and the second text according to the pre-training context model, wherein the pre-training context model can be understood as a pre-training context diagram, and the calculation formula of the text cosine similarity is as follows:wherein (1)>For text cosine similarity, P 1 For the first text, P 2 X is the second text i For P in the first text 1 The weight value of the ith word segment, y i For P in the second text 2 The weight value of the ith word segment in the list;
further, the public service system obtains the similarity of any word of the first text and any word of the second text according to the pre-trained context model so as to calculate the similarity of the text offsets of the first text and the second text.
Further, the public service system calculates text semantic similarity of the first text and the second text according to the text cosine similarity and the text offset similarity of the first text and the second text. Further, the public service system gathers all the second texts with the text semantic similarity larger than or equal to a preset value to obtain a third search text data set.
In an embodiment, obtaining the similarity of any word of the first text and any word of the second text according to the pre-trained contextual model to calculate the similarity of the text offsets of the first text and the second text comprises: according to the first text P 1 The word segmentation result of the first text P is obtained 1 Length of (2)And word S i At the first text P 1 Relative position +.>；
According to the second text P 2 The word segmentation result of the second text P is obtained 2 Length of (2)And word segmentation W j At the second text P 2 Relative position +.>；
Acquiring segmentation S i Is (are) adjacent to each otherDegree of harmony->And acquire the segmentation word W j Is +.>Degree of harmony->；
Calculating the similarity according to formula (1)；
Wherein (1)>Representing word S i And word segmentation W j A common neighboring point;
calculating the first text P according to formula (2) 1 And the second text P 2 Text offset similarity of (c)；
Wherein m is the first text P 1 The total number of the medium segmentation words, n is the second text P 2 Total number of medium-sized words.
Specifically, the public service system is based on the first text P 1 The word segmentation result of (1) to obtain a first text P 1 Length of (2)And word S i At the first text P 2 Relative position +.>。
Further, the public service system receives the second text P 2 The word segmentation result of the second text P is obtained 2 Length of (2)And word segmentation W j In the second text P 2 Relative position +.>；
Further, the public service system acquires the segmentation S i Is (are) adjacent to each otherDegree of harmony->And acquire the segmentation word W j Is +.>Degree of harmony->Similarity is calculated according to formula (1)>，Wherein (1)>Representing word S i And word segmentation W j A common neighbor point.
Further, the public service calculates the first text P according to formula (2) 1 And the second text P 2 Text offset similarity of (c)，Wherein m is the first text P 1 The total number of the medium segmentation words, n is the second text P 2 Total number of medium-sized words.
Further, the public service system calculates the text semantic similarity according to a calculation formula of the text semantic similarity, specifically:wherein S is text semantic phaseSimilarity.
According to the method and the device for searching the text semantic similarity, the search recommendation result is accurately obtained through the text semantic similarity, and the defect that the accuracy of the generated search recommendation result is low when the user does not search related categories before or the user acts less is overcome.
Fig. 3 illustrates a physical block diagram of a computer device, as shown in fig. 3, which may include: processor 310, communication interface (Communication Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. Processor 310 may invoke a computer program in memory 330 to perform steps to transfer a public service system based on technology, including, for example:
Analyzing the search operation service initiated by the user terminal to obtain a search task; the search task carries the identity information, the search keywords and the search quantity of the current search user; the current searching user is a user operating the user terminal;
searching a first search text data set according to the search keyword and the search quantity;
acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set;
determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set;
and collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present application further provide a non-transitory computer readable storage medium, where the non-transitory computer readable storage medium includes a computer program, where the computer program may be stored on the non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer program may be capable of executing the steps provided by the foregoing embodiments, where the steps include, for example:
analyzing the search operation service initiated by the user terminal to obtain a search task; the search task carries the identity information, the search keywords and the search quantity of the current search user; the current searching user is a user operating the user terminal;
searching a first search text data set according to the search keyword and the search quantity;
acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set;
determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set;
and collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user.
In yet another aspect, embodiments of the present application further provide a computer product including a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, is capable of performing the steps of transferring a public service system based on technology provided by the above embodiments, for example, including:
analyzing the search operation service initiated by the user terminal to obtain a search task; the search task carries the identity information, the search keywords and the search quantity of the current search user; the current searching user is a user operating the user terminal;
searching a first search text data set according to the search keyword and the search quantity;
acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set;
determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set;
and collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (6)
1. The public service system based on technology transfer is characterized by comprising a public service center, an analysis module, a search module, an acquisition module, a similarity calculation module and a text collection module; the public service center is respectively connected with the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module and is used for managing the analysis module, the search module, the acquisition module, the similarity calculation module and the text collection module;
the analysis module is used for: analyzing the search operation service initiated by the user terminal to obtain a search task; the search task carries the identity information, the search keywords and the search quantity of the current search user; the current searching user is a user operating the user terminal;
The search module is used for: searching a first search text data set according to the search keyword and the search quantity;
the acquisition module is used for: acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set;
the similarity calculation module is used for: determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set;
the text collection module is used for: collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user;
the identity information includes age information, sex information, education level information, and user social information;
the step of searching the user set according to the identity information acquisition target history comprises the following steps:
determining a first historical search user set associated with the current search user according to the age information, the gender information and the education level information;
determining a second historical search user set in the first historical search user set according to the user social information, and determining the second historical search user set as the target historical search user set;
The determining, according to the age information, the gender information and the education level information, a first historical search user set associated with the current search user includes:
calculating the age difference value between each historical searching user and the current searching user according to the age information;
determining the gender correlation coefficient of each historical searching user and the current searching user according to the gender information; the sex correlation coefficient of the same sex is 1, and the sex correlation coefficient of different sexes is 0.5;
determining a cultural difference degree coefficient of each historical searching user and the current searching user according to the education degree information;
calculating a relevancy coefficient according to the age difference value, the gender relevancy coefficient and the cultural difference degree coefficient of each historical searching user and the current searching user;
determining the first historical search user set according to the relevance coefficient of each historical search user and the current search user;
the calculation formula of the association coefficient is as follows:
wherein G is a relevance coefficient, A g For age difference, V g For the sex correlation coefficient, C g Is a cultural difference degree coefficient.
2. A technology-based transfer public service method, applied to the technology-based transfer public service system according to claim 1, comprising:
analyzing the search operation service initiated by the user terminal to obtain a search task; the search task carries the identity information, the search keywords and the search quantity of the current search user; the current searching user is a user operating the user terminal;
searching a first search text data set according to the search keyword and the search quantity;
acquiring a target historical search user set according to the identity information, and acquiring a second search text data set of the target historical search user set;
determining a third search text data set according to the text semantic similarity of the first search text data set and the second search text data set;
collecting the first search text data set and the third search text data set to obtain a target search text data set of the current search user;
the identity information includes age information, sex information, education level information, and user social information;
the step of searching the user set according to the identity information acquisition target history comprises the following steps:
Determining a first historical search user set associated with the current search user according to the age information, the gender information and the education level information;
determining a second historical search user set in the first historical search user set according to the user social information, and determining the second historical search user set as the target historical search user set;
the determining, according to the age information, the gender information and the education level information, a first historical search user set associated with the current search user includes:
calculating the age difference value between each historical searching user and the current searching user according to the age information;
determining the gender correlation coefficient of each historical searching user and the current searching user according to the gender information; the sex correlation coefficient of the same sex is 1, and the sex correlation coefficient of different sexes is 0.5;
determining a cultural difference degree coefficient of each historical searching user and the current searching user according to the education degree information;
calculating a relevancy coefficient according to the age difference value, the gender relevancy coefficient and the cultural difference degree coefficient of each historical searching user and the current searching user;
Determining the first historical search user set according to the relevance coefficient of each historical search user and the current search user;
the calculation formula of the association coefficient is as follows:wherein G is a relevance coefficient, A g For age difference, V g For the sex correlation coefficient, C g Is a cultural difference degree coefficient.
3. The technology-based transfer public service method of claim 2, wherein said determining a second set of historical search users from the first set of historical search users based on the user social information comprises:
determining a social relation tree of each user in the current searching user and the first historical searching user set according to the user social information; the social relation tree comprises a single-path tree and a multi-path tree;
if the social relation tree is determined to be a single-path tree, determining all users with the path length of the social relation tree being more than 5 in the first historical searching user set as the second historical searching user set; or alternatively, the first and second heat exchangers may be,
and if the social relation tree is determined to be a multi-path tree, determining all users including 3-level leaf nodes in the social relation tree in the first historical searching user set as the second historical searching user set.
4. The technology-based transfer public service method of claim 2, wherein said determining a third set of search text data based on text semantic similarity of the first set of search text data and the second set of search text data comprises:
acquiring a first text in the first search text data set and a second text in the second search text data set; the first text is located in any text in the first search text data set, and the second text is located in any text in the second search text data set;
calculating the text cosine similarity of the first text and the second text according to a pre-trained context model; the calculation formula of the text cosine similarity is as follows:
wherein (1)>For text cosine similarity, P 1 For the first text, P 2 X is the second text i For the first text P 1 The weight value of the ith word segment, y i For the second text P 2 The weight value of the ith word segment in the list;
obtaining the similarity of any word segmentation of the first text and any word segmentation of the second text according to the pre-training context model so as to calculate the similarity of the text offset of the first text and the second text;
Calculating the text semantic similarity of the first text and the second text according to the text cosine similarity and the text offset similarity of the first text and the second text;
and collecting all second texts with the text semantic similarity larger than or equal to a preset value to obtain the third search text data set.
5. The technology-based transfer public service method according to claim 4, wherein the obtaining the similarity of any one of the partial words of the first text and any one of the partial words of the second text according to the pre-trained context model to calculate the text offset similarity of the first text and the second text comprises:
according to the first text P 1 The word segmentation result of the first text P is obtained 1 Length of (2)And word S i At the first text P 1 Relative position +.>；
According to the second text P 2 The word segmentation result of the second text P is obtained 2 Length of (2)And word segmentation W j At the second text P 2 Relative position +.>；
Acquiring segmentation S i Is (are) adjacent to each otherDegree of harmony->And acquire the segmentation word W j Is +.>Degree of harmony；
Calculating the similarity according to formula (1)；
Wherein (1)>Representing word S i And word segmentation W j A common neighboring point;
calculating the first text P according to formula (2) 1 And the second text P 2 Text offset similarity of (c)；
Wherein m is the first text P 1 The total number of the medium segmentation words, n is the second text P 2 Total number of medium-sized words.
6. The technology-based transfer public service method according to claim 5, wherein the text semantic similarity is calculated by the following formula:wherein S is text semantic similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311463708.6A CN117194801B (en) | 2023-11-06 | 2023-11-06 | Public service transferring system and method based on technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311463708.6A CN117194801B (en) | 2023-11-06 | 2023-11-06 | Public service transferring system and method based on technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117194801A CN117194801A (en) | 2023-12-08 |
| CN117194801B true CN117194801B (en) | 2024-03-08 |
Family
ID=89002028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311463708.6A Active CN117194801B (en) | 2023-11-06 | 2023-11-06 | Public service transferring system and method based on technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117194801B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942279A (en) * | 2014-04-01 | 2014-07-23 | 百度(中国)有限公司 | Method and device for showing search result |
| CN110222265A (en) * | 2019-05-28 | 2019-09-10 | 深圳市轱辘汽车维修技术有限公司 | A kind of method, system, user terminal and the server of information push |
| WO2020057022A1 (en) * | 2018-09-18 | 2020-03-26 | 深圳壹账通智能科技有限公司 | Associative recommendation method and apparatus, computer device, and storage medium |
| CN113343091A (en) * | 2021-06-22 | 2021-09-03 | 力合科创集团有限公司 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
| CN115544285A (en) * | 2022-09-22 | 2022-12-30 | 杭州群核信息技术有限公司 | Three-dimensional model search recommendation method, device, equipment and medium |
| CN115827990A (en) * | 2023-02-10 | 2023-03-21 | 北京中电普华信息技术有限公司 | Searching method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10474704B2 (en) * | 2016-06-27 | 2019-11-12 | International Business Machines Corporation | Recommending documents sets based on a similar set of correlated features |
-
2023
- 2023-11-06 CN CN202311463708.6A patent/CN117194801B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942279A (en) * | 2014-04-01 | 2014-07-23 | 百度(中国)有限公司 | Method and device for showing search result |
| WO2020057022A1 (en) * | 2018-09-18 | 2020-03-26 | 深圳壹账通智能科技有限公司 | Associative recommendation method and apparatus, computer device, and storage medium |
| CN110222265A (en) * | 2019-05-28 | 2019-09-10 | 深圳市轱辘汽车维修技术有限公司 | A kind of method, system, user terminal and the server of information push |
| CN113343091A (en) * | 2021-06-22 | 2021-09-03 | 力合科创集团有限公司 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
| CN115544285A (en) * | 2022-09-22 | 2022-12-30 | 杭州群核信息技术有限公司 | Three-dimensional model search recommendation method, device, equipment and medium |
| CN115827990A (en) * | 2023-02-10 | 2023-03-21 | 北京中电普华信息技术有限公司 | Searching method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117194801A (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10642938B2 (en) | Artificial intelligence based method and apparatus for constructing comment graph | |
| CN108804641B (en) | Text similarity calculation method, device, equipment and storage medium | |
| CN108829822B (en) | Media content recommendation method and device, storage medium and electronic device | |
| JP6073345B2 (en) | Method and apparatus for ranking search results, and search method and apparatus | |
| CN111324784B (en) | Character string processing method and device | |
| CN108280114B (en) | Deep learning-based user literature reading interest analysis method | |
| CN113535974B (en) | Diagnostic recommendation method and related device, electronic equipment and storage medium | |
| WO2018157625A1 (en) | Reinforcement learning-based method for learning to rank and server | |
| US20080208836A1 (en) | Regression framework for learning ranking functions using relative preferences | |
| JP2009519543A (en) | Method and apparatus for building a compact similarity structure and method for using such a compact similarity structure for analyzing document relevance | |
| WO2008106668A1 (en) | User query mining for advertising matching | |
| CN109241243B (en) | Candidate document sorting method and device | |
| CN113342958B (en) | Question-answer matching method, text matching model training method and related equipment | |
| KR20190128246A (en) | Searching methods and apparatus and non-transitory computer-readable storage media | |
| CN111026877A (en) | Knowledge verification model construction and analysis method based on probability soft logic | |
| CN115374362A (en) | Multi-way recall model training method, multi-way recall device and electronic equipment | |
| CN116521936B (en) | Course recommendation method and device based on user behavior analysis and storage medium | |
| CN117194801B (en) | Public service transferring system and method based on technology | |
| Ozsoy | Utilizing fasttext for venue recommendation | |
| JP6521931B2 (en) | Model generation device, click log correct likelihood calculation device, document search device, method, and program | |
| US20160196619A1 (en) | Homogenizing time-based seniority signal with transition-based signal | |
| JP5832869B2 (en) | Keyword extraction system and keyword extraction method using category matching | |
| JP2011170699A (en) | Device, method and program for estimating knowledge amount in each field of retrieval system user | |
| CN116010728B (en) | Method for determining process flow presentation form of numerical control system and related equipment | |
| Hao et al. | Towards a query-less news search framework on twitter |
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 |