Intelligent collaboration system for resource parties based on data analysis

Abstract

A resource-side intelligent collaboration system based on data analysis is disclosed. It first obtains the resource demand text description published by the resource demander, and at the same time collects the solution text description provided by the alternative resource party, and introduces data processing and semantic understanding algorithms based on artificial intelligence and natural language processing technology at the back end to perform semantic analysis and matching of the resource demand text description and the solution text description, so as to determine whether the alternative resource party meets the needs of the resource demander. In this way, it can not only help the resource demander find suitable alternative resource parties more quickly, but also help the alternative resource party understand the market demand more accurately, realize the accurate allocation and optimal utilization of resources, and provide support for resource collaboration and cooperation.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent data analysis, and in particular to a resource-side intelligent collaboration system based on data analysis. Background Art

[0002] In business and production activities, resource-side collaboration refers to the sharing of resources, information and capabilities between different organizations or individuals to achieve a mutually beneficial and win-win partnership. This collaboration can involve various fields such as supply chain management, cooperative development, and sharing economy. Through resource-side collaboration, participants can better utilize their respective resources, improve efficiency, reduce costs, and create greater value.

[0003] With the development of globalization and technology, resource collaboration has become more complex, requiring efficient systems to handle large amounts of data and demand. However, traditional resource collaboration systems often have information island problems. Data sharing and communication between resource demanders and candidate resource parties are not smooth, resulting in information asymmetry and difficulty in accurately understanding each other's needs and capabilities, which affects the accuracy of resource matching. In addition, existing collaboration systems usually rely on manual screening and matching, which is labor-intensive, inefficient, and unable to respond to market changes and demand changes in a timely manner. Not only that, matching based on manual experience and simple rules is prone to errors and cannot fully take into account the complex correlation and matching between resource demanders and candidate resource parties.

[0004] Therefore, an optimized resource-side intelligent collaboration system is desired. Summary of the invention

[0005] The present disclosure is made in consideration of the above problems. One object of the present disclosure is to provide a resource-side intelligent collaboration system based on data analysis.

[0006] The embodiment of the present disclosure provides a resource-side intelligent collaboration system based on data analysis, which includes:

[0007] Resource requirement text collection module, used to obtain resource requirement text descriptions published by resource demanders;

[0008] A solution text collection module is used to obtain the solution text description provided by the candidate resource party;

[0009] A resource requirement and solution text semantic encoding module, used for performing word granularity-based semantic encoding on the resource requirement text description and the solution text description to obtain a sequence of resource requirement text description word granularity encoding vectors and a sequence of solution text description word granularity encoding vectors;

[0010] A semantic optimization module, used for inputting the sequence of the resource requirement text description word granularity encoding vectors and the sequence of the solution text description word granularity encoding vectors into a semantic optimization engine integrating semantic relevance and semantic span to obtain a sequence of optimized resource requirement text description word granularity encoding vectors and a sequence of optimized solution text description word granularity encoding vectors;

[0011] A local semantic matching coefficient calculation module, used to calculate the local semantic matching coefficient between the sequence of word granularity encoding vectors of the text description of the optimization resource requirements and the sequence of word granularity encoding vectors of the text description of the optimization solution;

[0012] The candidate resource party push judgment module is used to determine whether to push the candidate resource party to the resource demander based on the comparison between the local semantic matching coefficient and a predetermined threshold.

[0013] For example, according to the resource party intelligent collaboration system based on data analysis according to an embodiment of the present disclosure, the resource demand and solution text semantic encoding module includes:

[0014] A resource requirement text word granularity semantic encoding unit, used for performing word segmentation processing on the resource requirement text description and then passing it through a semantic encoder including a word embedding layer to obtain a sequence of word granularity encoding vectors of the resource requirement text description;

[0015] The solution text word granularity semantic encoding unit is used to obtain a sequence of word granularity encoding vectors of the solution text description after word segmentation processing is performed on the solution text description through the semantic encoder including the word embedding layer.

[0016] For example, according to the resource party intelligent collaboration system based on data analysis according to an embodiment of the present disclosure, the resource demand text word granularity semantic encoding unit includes:

[0017] A resource requirement word segmentation processing subunit, configured to perform word segmentation processing on the resource requirement text description to convert the resource requirement text description into a requirement word sequence consisting of a plurality of words;

[0018] A resource requirement embedding encoding subunit, configured to map each word in the requirement word sequence to a word vector using the word embedding layer of the semantic encoder including the word embedding layer to obtain a sequence of requirement word vectors;

[0019] The resource requirement semantic encoding subunit is used to use the semantic encoder including the word embedding layer to perform global context semantic encoding on the sequence of the requirement word vectors to obtain the sequence of the resource requirement text description word granularity encoding vectors.

[0020] For example, according to the resource-side intelligent collaboration system based on data analysis according to an embodiment of the present disclosure, the solution text word granularity semantic encoding unit includes:

[0021] A solution word segmentation processing subunit, configured to perform word segmentation processing on the solution text description to convert the solution text description into a solution word sequence consisting of a plurality of words;

[0022] A solution embedding encoding subunit, configured to map each word in the solution word sequence to a word vector using the word embedding layer of the semantic encoder including the word embedding layer to obtain a sequence of solution word vectors;

[0023] The solution semantic encoding subunit is used to use the semantic encoder including the word embedding layer to perform global context semantic encoding on the sequence of the solution word vectors to obtain the sequence of the solution text description word granularity encoding vectors.

[0024] For example, according to the resource-side intelligent collaboration system based on data analysis according to an embodiment of the present disclosure, the semantic optimization module includes:

[0025] An extraction unit, used for extracting a predetermined resource requirement text description word granularity encoding vector from the sequence of resource requirement text description word granularity encoding vectors;

[0026] A semantic relevance calculation unit, used for calculating the semantic relevance between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of resource requirement text description word granularity semantic relevances;

[0027] A global mean value calculation unit, used to calculate the global mean value of the sequence of granular semantic associations of the resource demand text description words to obtain a global average semantic association of the granular semantics of the resource demand text description words;

[0028] A weighted reinforcement unit is used to perform weighted reinforcement on the predetermined resource requirement text description word granularity encoding vector using the global average semantic association of the resource requirement text description word granularity as a weight to obtain an optimized resource requirement text description word granularity encoding vector corresponding to the predetermined resource requirement text description word granularity encoding vector.

[0029] For example, according to the resource-side intelligent collaboration system based on data analysis according to an embodiment of the present disclosure, the semantic relevance calculation unit is used to:

[0030] Calculating the semantic similarity between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of resource requirement text description word granularity semantic similarities;

[0031] Calculate the number of feature vectors between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of word granularity distance meter numbers;

[0032] The sequence of word granularity semantic similarities of the resource requirement text description is divided by the sequence of word granularity distance meter quantities by position to obtain a sequence of word granularity semantic associations of the resource requirement text description.

[0033] For example, according to the resource party intelligent collaboration system based on data analysis of an embodiment of the present disclosure, the alternative resource party push judgment module is used to determine whether to push the alternative resource party to the resource demander based on the comparison between the local semantic matching coefficient and a predetermined threshold.

[0034] For example, according to the resource party intelligent collaboration system based on data analysis according to an embodiment of the present disclosure, in response to the local semantic matching coefficient being greater than the predetermined threshold, it is determined to push the candidate resource party to the resource demander.

[0035] According to the resource party intelligent collaboration system based on data analysis of the embodiment of the present disclosure, it first obtains the resource demand text description published by the resource demand party, and at the same time collects the solution text description provided by the alternative resource party, and introduces data processing and semantic understanding algorithms based on artificial intelligence and natural language processing technology in the back end to perform semantic analysis and matching of the resource demand text description and the solution text description, so as to determine whether the alternative resource party meets the needs of the resource demand party. In this way, it can not only help the resource demand party find suitable alternative resource parties more quickly, but also help the alternative resource party understand market demand more accurately, realize accurate allocation and optimal utilization of resources, and provide support for resource coordination and cooperation. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings of the embodiments of the present disclosure. Obviously, the drawings described below only relate to some embodiments of the present disclosure, and are not intended to limit the present disclosure.

[0037] Figure 1 A schematic diagram of the application architecture of the resource party intelligent collaboration system based on data analysis in an embodiment of the present disclosure is shown;

[0038] Figure 2 A schematic diagram of the structure of a resource party intelligent collaboration system based on data analysis in an embodiment of the present disclosure is shown;

[0039] Figure 3A schematic diagram of the structure of a resource demand and solution text semantic coding module of a resource party intelligent collaboration system based on data analysis in an embodiment of the present disclosure is shown;

[0040] Figure 4 A schematic diagram of the structure of a semantic optimization module of a resource-side intelligent collaboration system based on data analysis in an embodiment of the present disclosure is shown;

[0041] Figure 5 A flow chart of a resource-side intelligent collaboration method based on data analysis in an embodiment of the present disclosure is shown;

[0042] Figure 6 An application scenario diagram of the resource party intelligent collaboration system based on data analysis in an embodiment of the present disclosure is shown; and

[0043] Figure 7 A schematic diagram of a storage medium according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present disclosure, rather than all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present disclosure.

[0045] The terms used in this specification are those general terms currently widely used in the art in consideration of the functions of the present disclosure, but these terms may vary according to the intention of a person of ordinary skill in the art, precedents, or new technologies in the art. In addition, specific terms may be selected by the applicant, and in this case, their detailed meanings will be described in the detailed description of the present disclosure. Therefore, the terms used in the specification should not be understood as simple names, but rather as an overall description based on the meaning of the terms and the present disclosure.

[0046] Although the present disclosure makes various references to certain modules in the system according to embodiments of the present disclosure, any number of different modules can be used and run on a user terminal and / or server. The modules are illustrative only, and different aspects of the systems and methods can use different modules.

[0047] Flowcharts are used in this disclosure to illustrate the operations performed by the system according to the embodiments of the present disclosure. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0048] Figure 1A schematic diagram of the application architecture of the resource-side intelligent collaboration system based on data analysis in an embodiment of the present disclosure is shown, including a server 100 and a terminal device 200.

[0049] The terminal device 200 and the server 100 can be connected via the Internet to achieve mutual communication. Optionally, the above-mentioned Internet uses standard communication technology and / or protocol. The Internet is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or a virtual private network. In some embodiments, the data exchanged through the network can be represented by technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec), etc. can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0050] The server 100 can provide various network services for the terminal device 200, wherein the server 100 can be a single server, a server cluster consisting of several servers, or a cloud computing center. Specifically, the server 100 may include a processor 110 (Center Processing Unit, CPU), a memory 120, an input device 130, and an output device 140, etc. The input device 130 may include a keyboard, a mouse, a touch screen, etc., and the output device 140 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a cathode ray tube (Cathode Ray Tube, CRT), etc.

[0051] The memory 120 may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor 110 with program instructions and data stored in the memory 120. In the embodiment of the present disclosure, the memory 120 may be used to store the corresponding method of the resource party intelligent collaboration system based on data analysis in the embodiment of the present disclosure.

[0052] The processor 110 calls the program instructions stored in the memory 120, and the processor 110 is used to execute the steps of any one of the resource-side intelligent collaboration methods based on data analysis in the embodiments of the present disclosure according to the obtained program instructions.

[0053] In addition, the application architecture diagram in the embodiment of the present disclosure is intended to more clearly illustrate the technical solution in the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided in the embodiment of the present disclosure. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present disclosure is also applicable to similar problems.

[0054] The following is a non-restrictive description of the resource-side intelligent collaboration system based on data analysis provided according to at least one embodiment of the present disclosure through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present disclosure.

[0055] With the development of big data technology, the ability to collect, store and process data has been greatly improved. Artificial intelligence technology, especially natural language processing (NLP) and machine learning, provides powerful tools for data collaborative analysis and matching, making it possible to extract useful information from massive data.

[0056] Based on this, in the technical solution of the present disclosure, a resource party intelligent collaboration system based on data analysis is proposed. In resource management, the use of data analysis technology can better understand and integrate the information between the resource demand party and the alternative resource party, and realize the efficient use and collaboration of resources. Specifically, the technical concept of the present disclosure is to obtain the text description of resource requirements published by the resource demand party, and at the same time collect the text description of solutions provided by the alternative resource party, and introduce data processing and semantic understanding algorithms based on artificial intelligence and natural language processing technology in the back end to perform semantic analysis and matching of the resource demand text description and the solution text description, so as to judge whether the alternative resource party meets the needs of the resource demand party. In this way, it can not only help the resource demand party to find suitable alternative resource parties more quickly, but also help the alternative resource party to understand the market demand more accurately, realize the accurate allocation and optimal utilization of resources, and provide support for the coordination and cooperation of resources.

[0057] Figure 2The schematic diagram of the structure of the resource party intelligent collaboration system 800 based on data analysis in the embodiment of the present disclosure is shown. The resource party intelligent collaboration system 800 based on data analysis includes: a resource demand text acquisition module 810, which is used to obtain the resource demand text description published by the resource demand party; a solution text acquisition module 820, which is used to obtain the solution text description provided by the alternative resource party; a resource demand and solution text semantic encoding module 830, which is used to perform word granularity-based semantic encoding on the resource demand text description and the solution text description to obtain a sequence of resource demand text description word granularity encoding vectors and a sequence of solution text description word granularity encoding vectors; a semantic optimization module 840, which is used to convert the sequence of resource demand text description word granularity encoding vectors into a sequence of word granularity encoding vectors. The sequence of columns and the solution text description word granularity encoding vectors is input into a semantic optimization engine that integrates semantic relevance and semantic span to obtain a sequence of optimized resource demand text description word granularity encoding vectors and a sequence of optimized solution text description word granularity encoding vectors; a local semantic matching coefficient calculation module 850 is used to calculate the local semantic matching coefficient between the sequence of optimized resource demand text description word granularity encoding vectors and the sequence of optimized solution text description word granularity encoding vectors; an alternative resource party push judgment module 860 is used to determine whether to push the alternative resource party to the resource demand party based on the comparison between the local semantic matching coefficient and a predetermined threshold.

[0058] More specifically, in the technical solution disclosed in the present invention, first, a text description of resource requirements published by a resource demander is obtained, and a text description of a solution provided by an alternative resource party is obtained. Next, it is considered that the text description of resource requirements contains the semantics and feature information of the requirements of the resource demander, and the text description of the solution contains the resource support and semantic features that the alternative resource party can provide. Therefore, in order to be able to perform semantic understanding and feature extraction on the resource requirement text and the solution text, so that the semantics of the two can be subsequently analyzed and matched in a high-dimensional space to determine whether the resource support and solution that the alternative resource party can provide can meet the resource demander, in the technical solution disclosed in the present invention, the resource requirement text description is further processed by word segmentation and then passed through a semantic encoder containing a word embedding layer to obtain a sequence of word granularity encoding vectors of the resource requirement text description, and the solution text description is processed by word segmentation and then passed through a semantic encoder containing a word embedding layer to obtain a sequence of word granularity encoding vectors of the solution text description. Through word segmentation, the continuous text description can be decomposed into basic text semantic units, and then, the word embedding layer is used to convert each word into a vector form of computer language, and the semantic feature information of each word is captured. Therefore, through the processing of the semantic encoder including the word embedding layer, the contextual semantic association feature information based on word granularity in the resource demand text description and the solution text description can be learned and captured respectively. These features can be used for subsequent machine learning model training and text similarity calculation, helping the system to better understand the text content, and matching the text semantics of the two to determine whether to push the alternative resource party to the resource demand party.

[0059] Accordingly, if Figure 3 As shown, the resource requirement and solution text semantic encoding module 830 includes: a resource requirement text word granularity semantic encoding unit 831, which is used to perform word segmentation processing on the resource requirement text description and then pass it through a semantic encoder including a word embedding layer to obtain a sequence of word granularity encoding vectors of the resource requirement text description; a solution text word granularity semantic encoding unit 832, which is used to perform word segmentation processing on the solution text description and then pass it through the semantic encoder including a word embedding layer to obtain a sequence of word granularity encoding vectors of the solution text description.

[0060] Among them, the resource requirement text word granularity semantic encoding unit 831 includes: a resource requirement word segmentation processing subunit, which is used to perform word segmentation processing on the resource requirement text description to convert the resource requirement text description into a requirement word sequence composed of multiple words; a resource requirement embedding encoding subunit, which is used to use the word embedding layer of the semantic encoder including the word embedding layer to map each word in the requirement word sequence to a word vector to obtain a sequence of requirement word vectors; a resource requirement semantic encoding subunit, which is used to use the semantic encoder including the word embedding layer to perform global context-based semantic encoding on the sequence of requirement word vectors to obtain a sequence of word granularity encoding vectors of the resource requirement text description.

[0061] Among them, the solution text word granularity semantic encoding unit 832 includes: a solution word segmentation processing subunit, which is used to perform word segmentation processing on the solution text description to convert the solution text description into a solution word sequence composed of multiple words; a solution embedding encoding subunit, which is used to use the word embedding layer of the semantic encoder including the word embedding layer to map each word in the solution word sequence to a word vector to obtain a sequence of solution word vectors; a solution semantic encoding subunit, which is used to use the semantic encoder including the word embedding layer to perform global context-based semantic encoding on the sequence of solution word vectors to obtain a sequence of solution text description word granularity encoding vectors.

[0062] Furthermore, considering that the sequence of word granularity encoding vectors for the resource requirement text description and the sequence of word granularity encoding vectors for the solution text description respectively contain contextual semantic encoding features based on word granularity in the resource requirement text and the solution text, the contextual semantic features of each word are not equally important. This importance is not only related to the actual semantics of each word, but also to the semantic relevance and word span between words. Based on this, in order to further refine and enhance the key semantic information in the resource requirement text description and the solution text description so that they can more accurately reflect the important meaning of the original text, in the technical solution of the present disclosure, the sequence of word granularity encoding vectors for the resource requirement text description and the sequence of word granularity encoding vectors for the solution text description are input into a semantic optimization engine that integrates semantic relevance and semantic span to obtain a sequence of optimized word granularity encoding vectors for the resource requirement text description and a sequence of optimized word granularity encoding vectors for the solution text description. Through the processing of the semantic optimization engine that integrates semantic relevance and semantic span, the intrinsic association semantics and word granularity semantic span of each word in the resource demand text description and the solution text description can be automatically learned and captured, and this information can be used to dynamically adjust the importance weight of each word to adapt to the ever-changing data and needs. In this way, the respective expressions of the resource demand text semantics and the solution text semantics can be optimized respectively, thereby highlighting the important semantic features therein, which helps to better capture the semantic relevance and synergistic association between resource demand and solution in the future, thereby improving the matching quality between resource demanders and alternative resource parties.

[0063] Accordingly, if Figure 4 As shown, the semantic optimization module 840 includes: an extraction unit 841, which is used to extract a predetermined resource requirement text description word granularity encoding vector from the sequence of the resource requirement text description word granularity encoding vector; a semantic association calculation unit 842, which is used to calculate the semantic association between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of resource requirement text description word granularity semantic associations; a global mean calculation unit 843, which is used to calculate the global mean of the sequence of resource requirement text description word granularity semantic associations to obtain the global average semantic association of resource requirement text description word granularity; a weighted reinforcement unit 844, which is used to use the global average semantic association of the resource requirement text description word granularity as a weight to perform weighted reinforcement on the predetermined resource requirement text description word granularity encoding vector to obtain an optimized resource requirement text description word granularity encoding vector corresponding to the predetermined resource requirement text description word granularity encoding vector.

[0064] Among them, the semantic association calculation unit 842 is used to: calculate the semantic similarity between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of resource requirement text description word granularity semantic similarities; calculate the number of feature vectors between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of word granularity distance meter numbers; divide the sequence of resource requirement text description word granularity semantic similarities and the sequence of word granularity distance meter numbers by position to obtain a sequence of resource requirement text description word granularity semantic associations.

[0065] In a specific example, the semantic optimization module 840 is used to: input the sequence of the resource requirement text description word granularity encoding vectors into the semantic optimization engine integrating semantic relevance and semantic span to process with the following optimization formula to obtain the sequence of the optimized resource requirement text description word granularity encoding vectors; wherein the optimization formula is: ;in, and Respectively represent the sequence of granular encoding vectors of the resource requirement text description words and resource requirement text description word granularity encoding vector, express and The number of eigenvectors between express and The similarity between The total number of feature vectors in the sequence of granular encoding vectors representing the resource requirement text description word minus one, and The values ​​of are equal, The first in the sequence of the granular encoding vectors of the text description word of the optimization resource requirement Optimize resource requirements text description word granularity encoding vector.

[0066] Then, since the sequence of word granularity encoding vectors of the text description of the optimized resource requirements and the sequence of word granularity encoding vectors of the text description of the optimized solution respectively contain the word granularity semantic features in the text description of the resource requirements and the text description of the solution after the important semantics of the text are highlighted, the semantic features of this word granularity can reflect the semantic information of the resource requirements and the solution from the smallest semantic unit. In order to be able to perform interactive matching analysis on the semantic features of the two, so as to determine the degree of adaptation of the resource demand side and the alternative resource side, in the technical scheme disclosed in the present invention, the local semantic matching coefficient between the sequence of word granularity encoding vectors of the text description of the optimized resource requirements and the sequence of word granularity encoding vectors of the text description of the optimized solution is further calculated. By calculating the local semantic matching coefficient of the word granularity semantic features of the two, the semantic matching degree between the text description of the resource requirements and the text description of the solution based on the word granularity semantic unit can be quantified. It is worth mentioning that the local semantic matching coefficient can analyze the semantic similarity and interactive correlation between the texts in more detail, rather than just the overall matching degree. In other words, this matching coefficient can help the system evaluate the matching degree of each solution with the resource requirements, so as to more accurately find the solution that best matches the resource requirements to determine the most suitable alternative resource side.

[0067] Correspondingly, the candidate resource push determination module 860 is used to determine whether to push the candidate resource to the resource demander based on a comparison between the local semantic matching coefficient and a predetermined threshold.

[0068] In a specific example, the candidate resource push judgment module 860 is used to calculate the local semantic matching coefficient between the sequence of the optimized resource requirement text description word granularity encoding vector and the sequence of the optimized solution text description word granularity encoding vector using the following local matching formula; wherein the local matching formula is: ;in, is the first in the sequence of the word granularity encoding vector of the text description of the optimized resource requirement Optimize resource requirements text description word granularity encoding vector, is the first in the sequence of granular encoding vectors of the text description words of the optimization solution Optimized solution text description word granularity encoding vector, represents the Frobenius norm of a vector, Represents the eigenvalues ​​of each position in the resource demand-solution text semantic cosine similarity matrix, yes , The number of feature vectors in the sequence of word granularity encoding vectors for the optimized resource requirement text description, is the feature value of each position in the resource demand-solution text semantic attention matrix, The number of feature vectors in the sequence of word granularity encoding vectors describing the optimization solution text, is the feature value of each position in the solution-resource requirement text semantic attention matrix, It is The attention weight value of the granularity encoding feature of the text description word of the solution corresponding to the granularity encoding vector of the text description word of the optimization resource requirement, The first in the sequence of semantic encoding feature vectors of the word granularity in the text description of the attention resource demand A semantic encoding feature vector of the word granularity of the resource demand text description, yes The inverse temperature coefficient of the function, Indicates The attention weight value of the resource requirement text description encoding feature corresponding to the granular encoding vector of the text description word of the optimization solution, Indicates the first in the sequence of feature vectors encoding the solution text description A feature vector encoding the text description of the attention solution, represents the eigenvalues ​​of each position in the enhanced resource requirement-solution semantic cosine similarity matrix, represents the eigenvalues ​​of each position in the enhanced solution-resource requirement semantic cosine similarity matrix, is a hyperparameter, represents the local matching coefficient, Indicated by natural constant An exponential function with base .

[0069] Furthermore, based on the comparison between the local semantic matching coefficient and the predetermined threshold, it is determined whether to push the alternative resource party to the resource demander. In other words, the semantic interaction and matching features based on word granularity between the resource demand text and the solution text are compared with the predetermined threshold, and in response to the local semantic matching coefficient being greater than the predetermined threshold, it is determined to push the alternative resource party to the resource demander. In this way, it can not only help the resource demander find suitable alternative resource parties more quickly, but also help the alternative resource party to understand market demand more accurately, realize accurate allocation and optimal utilization of resources, and provide support for resource coordination and cooperation.

[0070] In a preferred example, the applicant of the present disclosure considers the sequence of word granularity encoding vectors of the optimized resource requirement text description and the sequence of word granularity encoding vectors of the optimized solution text description, and respectively performs semantic optimization fusion based on semantic relevance and semantic span for the text semantic features based on word segmentation embedding of the resource requirement text description released by the resource demander and the solution text description provided by the alternative resource party. In this way, due to the semantic differences of the source texts, the sequence of word granularity encoding vectors of the optimized resource requirement text description and the sequence of word granularity encoding vectors of the optimized solution text description will also have significant differences in the distribution of text semantic features, so that there are local overflow features when mapping to the common semantic matching domain, which affects the calculation accuracy of the local semantic matching coefficient between the sequence of word granularity encoding vectors of the optimized resource requirement text description and the sequence of word granularity encoding vectors of the optimized solution text description.

[0071] Based on this, calculating the local semantic matching coefficient between the sequence of the optimized resource requirement text description word granularity encoding vectors and the sequence of the optimized solution text description word granularity encoding vectors includes the following optimization steps: cascading the local semantic matching coefficients between the sequence of the optimized resource requirement text description word granularity encoding vectors and the sequence of the optimized solution text description word granularity encoding vectors into an optimized resource requirement-optimized solution text description joint encoding vector; calculating the optimized resource requirement-optimized solution text description joint encoding and representation matrix and the optimized resource requirement-optimized solution text description joint encoding difference representation matrix of the optimized resource requirement-optimized solution text description joint encoding vector, wherein the optimization The value of each position of the resource requirement-optimization solution text description joint coding and representation matrix is ​​the mean of a pair of eigenvalues ​​of the two positions of the optimized resource requirement-optimization solution text description joint coding vector corresponding to the position coordinates respectively, and the value of each position of the optimized resource requirement-optimization solution text description joint coding difference representation matrix is ​​the absolute value of the difference between a pair of eigenvalues ​​of the two positions of the optimized resource requirement-optimization solution text description joint coding vector corresponding to the position coordinates respectively; the transposed vector of the optimized resource requirement-optimization solution text description joint coding vector is matrix-multiplied with the optimized resource requirement-optimization solution text description joint coding and representation matrix to obtain the optimized resource requirement -Optimize the solution text description joint coding and representation vector and perform matrix multiplication of the optimization resource requirement-optimization solution text description joint coding difference representation matrix with the optimization resource requirement-optimization solution text description joint coding vector to obtain the optimization resource requirement-optimization solution text description joint coding difference representation vector, wherein the optimization resource requirement-optimization solution text description joint coding vector is a column vector; calculate the point sum of the optimization resource requirement-optimization solution text description joint coding and representation vector and the transposed vector of the optimization resource requirement-optimization solution text description joint coding difference representation vector to obtain the first optimization resource requirement-optimization solution text description joint coding and difference representation vector; calculate Calculate the matrix product of the optimized resource requirement-optimized solution text description joint coding and representation matrix and the optimized resource requirement-optimized solution text description joint coding difference representation matrix, and perform matrix multiplication of the transposed vector of the optimized resource requirement-optimized solution text description joint coding vector and the matrix product to obtain a second optimized resource requirement-optimized solution text description joint coding and difference representation vector; calculate the point sum of the first optimized resource requirement-optimized solution text description joint coding and difference representation vector and the transposed vector of the second optimized resource requirement-optimized solution text description joint coding and difference representation vector to obtain a corrected optimized resource requirement-optimized solution text description joint coding vector;The corrected optimization resource requirement-optimization solution text description joint encoding vector is split into a corrected optimization resource requirement text description word granularity encoding vector sequence and a corrected optimization solution text description word granularity encoding vector sequence based on the cascade of the optimization resource requirement text description word granularity encoding vector sequence and the optimization solution text description word granularity encoding vector sequence; and the local semantic matching coefficient between the corrected optimization resource requirement text description word granularity encoding vector sequence and the corrected optimization solution text description word granularity encoding vector sequence is calculated. ;

[0072] Based on this, the optimized resource requirement-optimized solution text description joint encoding vector and the optimized resource requirement-optimized solution text description joint encoding vector sum representation matrix and the optimized resource requirement-optimized solution text description joint encoding vector difference representation matrix are used as the retrieval and responsive distribution enhancement of the optimized resource requirement-optimized solution text description joint encoding vector for the joint semantic representation of the sequence of the optimized resource requirement text description word granularity encoding vector and the sequence of the optimized solution text description word granularity encoding vector, and the optimized resource requirement-optimized solution text description is constructed. The reference-free distributed retrieval response framework under the open domain of the joint coding vector based on group aggregation feature distribution is used to avoid the distribution response redundancy caused by the local overflow characteristics of the optimized resource demand-optimized solution text description joint coding vector through response superposition, so as to realize the faithfulness constraint of the self-aggregation statistics correlation of the response sequence of the optimized resource demand text description word granularity coding vector and the sequence of the optimized solution text description word granularity coding vector to the target common semantic matching domain, and improve the calculation accuracy of the local semantic matching coefficient between the sequence of the optimized resource demand text description word granularity coding vector and the sequence of the optimized solution text description word granularity coding vector. In this way, the semantic matching between resource demand and solution can be performed more accurately, so as to judge whether the alternative resource party meets the needs of the resource demand party, which is conducive to the accurate configuration and optimal utilization of resources.

[0073] Based on the above embodiments, see Figure 5 FIG. 1 is a flowchart of a resource-side intelligent collaboration method based on data analysis in an embodiment of the present disclosure. For example, the resource-side intelligent collaboration method based on data analysis can be executed by a server, which can be Figure 1 The server 100 shown in FIG. Figure 5As shown, according to the embodiment of the present disclosure, the intelligent resource collaboration method based on data analysis includes the following steps: S510, obtaining a resource demand text description published by a resource demander; S520, obtaining a solution text description provided by an alternative resource party; S530, performing word granularity-based semantic encoding on the resource demand text description and the solution text description to obtain a sequence of resource demand text description word granularity encoding vectors and a sequence of solution text description word granularity encoding vectors; S540, inputting the sequence of resource demand text description word granularity encoding vectors and the sequence of solution text description word granularity encoding vectors into a semantic optimization engine that integrates semantic relevance and semantic span to obtain a sequence of optimized resource demand text description word granularity encoding vectors and a sequence of optimized solution text description word granularity encoding vectors; S550, calculating the local semantic matching coefficient between the sequence of optimized resource demand text description word granularity encoding vectors and the sequence of optimized solution text description word granularity encoding vectors; S560, determining whether to push the alternative resource party to the resource demander based on a comparison between the local semantic matching coefficient and a predetermined threshold.

[0074] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned resource-side intelligent collaboration method based on data analysis have been referred to above. Figures 2 to 4 The resource-side intelligent collaborative system 800 based on data analysis has been introduced in detail, and therefore, its repeated description will be omitted.

[0075] Figure 6 FIG. 1 is an application scenario diagram of a resource party intelligent collaboration system based on data analysis according to an embodiment of the present disclosure. Figure 6 As shown, in this application scenario, first, a resource demand text description (for example, Figure 6 D1) and a textual description of the solution provided by the alternative resource party (e.g. Figure 6 Then, the resource requirement text description and the solution text description are input to a server (for example, Figure 6 In S) as shown in , the server is capable of using the resource party intelligent collaborative algorithm based on data analysis to process the resource requirement text description and the solution text description to determine whether to push the alternative resource party to the resource demander.

[0076] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present disclosure. In some possible implementations, the electronic device in the embodiments of the present disclosure may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the resource party intelligent collaboration method based on data analysis in the above embodiments when executing the program.

[0077] For example, the electronic device is disclosed in the present invention Figure 1 Taking the server 100 in the example as an example, the processor in the electronic device is the processor 110 in the server 100, and the memory in the electronic device is the memory 120 in the server 100.

[0078] An embodiment of the present disclosure also provides a computer-readable storage medium. Figure 7 FIG. 1 is a schematic diagram of a computer-readable storage medium 1000 according to an embodiment of the present disclosure. Figure 7 As shown, the computer-readable storage medium 1000 stores computer-executable instructions 1001. When the computer-executable instructions 1001 are executed by the processor, the resource-side intelligent collaboration method based on data analysis according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc.

[0079] The embodiments of the present disclosure also provide a computer program product or a computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer executable instructions from the computer-readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the resource-side intelligent collaboration method based on data analysis according to the embodiments of the present disclosure.

[0080] Those skilled in the art will appreciate that the contents disclosed in this disclosure may be subject to various modifications and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0081] In addition, although the present disclosure makes various references to certain units in the system according to embodiments of the present disclosure, any number of different units may be used and run on the client and / or server. The units are illustrative only, and different aspects of the systems and methods may use different units.

[0082] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of a software functional module. The present disclosure is not limited to any particular form of combination of hardware and software.

[0083] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0084] The above is an explanation of the present disclosure and should not be considered as a limitation thereof. Although several exemplary embodiments of the present disclosure have been described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present disclosure. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined in the claims. It should be understood that the above is an explanation of the present disclosure and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.

Claims

1. A resource-side intelligent collaboration system based on data analysis, characterized in that: include: Resource requirement text collection module, used to obtain resource requirement text descriptions published by resource demanders; A solution text collection module is used to obtain the solution text description provided by the candidate resource party; A resource requirement and solution text semantic encoding module, used for performing word granularity-based semantic encoding on the resource requirement text description and the solution text description to obtain a sequence of resource requirement text description word granularity encoding vectors and a sequence of solution text description word granularity encoding vectors; A semantic optimization module, used for inputting the sequence of the resource requirement text description word granularity encoding vectors and the sequence of the solution text description word granularity encoding vectors into a semantic optimization engine integrating semantic relevance and semantic span to obtain a sequence of optimized resource requirement text description word granularity encoding vectors and a sequence of optimized solution text description word granularity encoding vectors; A local semantic matching coefficient calculation module, used to calculate the local semantic matching coefficient between the sequence of word granularity encoding vectors of the text description of the optimization resource requirements and the sequence of word granularity encoding vectors of the text description of the optimization solution; A candidate resource party push judgment module, used to determine whether to push the candidate resource party to the resource demander based on a comparison between the local semantic matching coefficient and a predetermined threshold; Wherein, the semantic optimization module includes: An extraction unit, used for extracting a predetermined resource requirement text description word granularity encoding vector from the sequence of resource requirement text description word granularity encoding vectors; A semantic relevance calculation unit, used for calculating the semantic relevance between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of resource requirement text description word granularity semantic relevances; A global mean value calculation unit, used to calculate the global mean value of the sequence of granular semantic associations of the resource demand text description words to obtain a global average semantic association of the granular semantics of the resource demand text description words; A weighted reinforcement unit is used to perform weighted reinforcement on the predetermined resource requirement text description word granularity encoding vector using the global average semantic association of the resource requirement text description word granularity as a weight to obtain an optimized resource requirement text description word granularity encoding vector corresponding to the predetermined resource requirement text description word granularity encoding vector.

2. The resource-side intelligent collaboration system based on data analysis according to claim 1 is characterized in that: The resource requirement and solution text semantic encoding module includes: A resource requirement text word granularity semantic encoding unit, used for performing word segmentation processing on the resource requirement text description and then passing it through a semantic encoder including a word embedding layer to obtain a sequence of word granularity encoding vectors of the resource requirement text description; The solution text word granularity semantic encoding unit is used to obtain a sequence of word granularity encoding vectors of the solution text description after word segmentation processing is performed on the solution text description through the semantic encoder including the word embedding layer.

3. The resource-side intelligent collaboration system based on data analysis according to claim 2 is characterized in that: The resource demand text word granularity semantic encoding unit includes: A resource requirement word segmentation processing subunit, configured to perform word segmentation processing on the resource requirement text description to convert the resource requirement text description into a requirement word sequence consisting of a plurality of words; A resource requirement embedding encoding subunit, configured to map each word in the requirement word sequence to a word vector using the word embedding layer of the semantic encoder including the word embedding layer to obtain a sequence of requirement word vectors; The resource requirement semantic encoding subunit is used to use the semantic encoder including the word embedding layer to perform global context semantic encoding on the sequence of the requirement word vectors to obtain the sequence of the resource requirement text description word granularity encoding vectors.

4. The resource-side intelligent collaboration system based on data analysis according to claim 3 is characterized in that: The solution text word granularity semantic encoding unit includes: A solution word segmentation processing subunit, configured to perform word segmentation processing on the solution text description to convert the solution text description into a solution word sequence consisting of a plurality of words; A solution embedding encoding subunit, configured to map each word in the solution word sequence to a word vector using the word embedding layer of the semantic encoder including the word embedding layer to obtain a sequence of solution word vectors; The solution semantic encoding subunit is used to use the semantic encoder including the word embedding layer to perform global context semantic encoding on the sequence of the solution word vectors to obtain the sequence of the solution text description word granularity encoding vectors.

5. The resource-side intelligent collaboration system based on data analysis according to claim 4 is characterized in that: The semantic relevance calculation unit is used to: Calculating the semantic similarity between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of resource requirement text description word granularity semantic similarities; Calculate the number of feature vectors between the predetermined resource requirement text description word granularity encoding vector and all other resource requirement text description word granularity encoding vectors to obtain a sequence of word granularity distance meter numbers; The sequence of word granularity semantic similarities of the resource requirement text description is divided by the sequence of word granularity distance meter quantities by position to obtain a sequence of word granularity semantic associations of the resource requirement text description.

6. The resource-side intelligent collaboration system based on data analysis according to claim 5 is characterized in that: The candidate resource push judgment module is used to determine whether to push the candidate resource to the resource demander based on a comparison between the local semantic matching coefficient and a predetermined threshold.

7. The resource-side intelligent collaboration system based on data analysis according to claim 6 is characterized in that: In response to the local semantic matching coefficient being greater than the predetermined threshold, it is determined to push the candidate resource party to the resource demander.

Images