A method, device, equipment and medium for identifying upstream and downstream relationships of an enterprise

Abstract

This invention relates to the field of text data processing technology, and in particular to a method, apparatus, device, and medium for identifying upstream and downstream relationships between enterprises. The method includes: obtaining the industrial chain points corresponding to each enterprise object based on enterprise information corresponding to several enterprise objects and a preset chain point prediction model; clustering the several enterprise objects to determine the category label of each enterprise object; obtaining the associated product labels and associated technology labels of the target product based on several product description texts in the enterprise object corresponding to any target product; combining the preset label weights corresponding to the labels to obtain the association similarity between two enterprise objects; and identifying the upstream and downstream relationship between the two enterprise objects when the association similarity is greater than a preset similarity threshold. This invention can accurately determine the association similarity between two enterprise objects, making the judgment of the upstream and downstream relationship between two enterprise objects more accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of text data processing, and in particular to a method, device, equipment and medium for identifying upstream and downstream relationships of enterprises. Background Art

[0002] The upstream and downstream relationship of an enterprise refers to the relationship between upstream and downstream enterprises determined based on the supply relationship. For example, in the public documents released by the enterprise, users can view the material sources and sales destinations of the products sold by the enterprise, thereby determining some upstream and downstream enterprises associated with the enterprise. However, the records in public documents are limited and can only record some related enterprises. It is impossible to know whether other enterprises have upstream and downstream relationships with the enterprise. Usually, the health status of an enterprise's upstream and downstream enterprises directly affects the operating status of the enterprise. Therefore, in many scenarios, such as risk assessment of enterprises or industry correlation analysis, people hope to accurately know the upstream and downstream relationships of enterprises. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device, equipment and medium for identifying upstream and downstream relationships of enterprises, which can accurately obtain the association similarity between two enterprise objects, so that the judgment of the upstream and downstream relationship between the two enterprise objects is more accurate and reliable.

[0004] According to a first aspect of the present invention, a method for identifying upstream and downstream relationships of an enterprise is provided, comprising the following steps:

[0005] According to the enterprise information corresponding to a given number of enterprise objects and a preset chain point prediction model, the industrial chain chain point corresponding to each enterprise object is obtained; the enterprise information corresponding to the enterprise object includes the enterprise object name and the product introduction information of the enterprise object.

[0006] Based on a number of preset enterprise category words and according to the product introduction information of each enterprise object, a number of enterprise objects are clustered to determine the category label of each enterprise object.

[0007] For the target product of any enterprise object, several target product keywords are extracted through the keyword extraction model according to several product description texts in the enterprise object corresponding to the target product, so as to obtain the associated product tags and associated technical tags of the target product.

[0008] The label similarities corresponding to the category labels, associated product labels and associated technical labels between every two enterprise objects are calculated, and the label similarities are weighted and calculated according to the preset label weights corresponding to the category labels, associated product labels and associated technical labels to obtain the association similarity between every two enterprise objects.

[0009] When the association similarity between two enterprise objects is greater than a preset similarity threshold, the upstream and downstream relationship between the two enterprise objects is identified according to the industrial chain points corresponding to the two enterprise objects.

[0010] Furthermore, the chain point prediction model is constructed through the following steps:

[0011] According to a number of industrial chain points in a given industrial chain, the output layer of the preset neural network prediction model is configured.

[0012] The pre-acquired enterprise information sample sets are respectively input into the preset neural network prediction model to extract text features, and a number of text feature vectors are obtained; the enterprise information sample sets include the names of enterprise object samples and product introduction information of enterprise object samples.

[0013] A number of text feature vectors are used to train the preset neural network prediction model, and the predicted industrial chain points corresponding to each enterprise object sample are obtained from the output layer.

[0014] According to the predicted industrial chain points and actual industrial chain points corresponding to each enterprise object sample, the preset neural network prediction model is iteratively adjusted to construct a chain point prediction model.

[0015] Furthermore, the category label of the enterprise object is determined through the following steps:

[0016] According to the number of enterprise category words, the same number of clusters to be clustered are constructed, and the word vector of each enterprise category word is used as the center of each cluster to be clustered.

[0017] For any enterprise object, a number of enterprise object keywords are extracted from the product introduction information of the enterprise object and form an enterprise keyword group.

[0018] The distance between the phrase vector of the enterprise keyword group and each cluster center to be clustered is calculated to determine the target cluster center; the target cluster center refers to the cluster center to be clustered that is closest to the phrase vector of the enterprise keyword group.

[0019] The enterprise category word corresponding to the target cluster center is determined as the category label of the enterprise object.

[0020] Furthermore, the associated product tags and associated technical tags of the target product are obtained through the following steps:

[0021] The TF-IDF value corresponding to each target product keyword is calculated, and the target product keyword whose corresponding TF-IDF value is greater than a preset TF-IDF threshold is determined as a target product associated word.

[0022] The trained natural language processing model is used to obtain product entity words and technical entity words from the target product related words, and the product entity words and technical entity words are used as the associated product labels and associated technology labels of the target product respectively.

[0023] Furthermore, the preset label weights corresponding to the category labels are obtained through the following steps:

[0024] For the same cluster center to be clustered, several enterprise keyword groups corresponding to the cluster center to be clustered are obtained.

[0025] For any enterprise keyword group corresponding to the center of the cluster to be clustered, a target distance interval corresponding to the enterprise keyword group is mapped from a number of preset distance intervals according to the distance between the phrase vector of the enterprise keyword group and the center of the cluster to be clustered.

[0026] According to the comparison table of preset distance intervals and preset weight coefficients, the preset weight coefficient corresponding to the target distance interval is determined as the preset weight coefficient corresponding to the enterprise keyword group.

[0027] When calculating the association similarity between two enterprise objects, the preset tag weight corresponding to the category tag is obtained according to the preset weight coefficients corresponding to the enterprise keyword groups of the two enterprise objects themselves and the given tag weight corresponding to the category tag.

[0028] According to a second aspect of the present invention, there is provided a device for identifying upstream and downstream relationships of enterprises, the device comprising:

[0029] The first acquisition module is used to obtain the industrial chain chain point corresponding to each enterprise object based on the enterprise information corresponding to a given number of enterprise objects and a preset chain point prediction model; the enterprise information corresponding to the enterprise object includes the enterprise object name and the product introduction information of the enterprise object.

[0030] The first determination module is used to cluster a plurality of enterprise objects based on a plurality of preset enterprise category words and according to the product introduction information of each enterprise object, and determine a category label for each enterprise object.

[0031] The second acquisition module is used to extract several target product keywords for any target product of an enterprise object according to several product description texts in the enterprise object corresponding to the target product through a keyword extraction model to obtain associated product tags and associated technical tags of the target product.

[0032] The calculation module is used to calculate the label similarities corresponding to the category labels, associated product labels and associated technical labels between every two enterprise objects, and to weight and calculate the label similarities according to the preset label weights corresponding to the category labels, associated product labels and associated technical labels to obtain the associated similarity between every two enterprise objects.

[0033] The identification module is used to identify the upstream and downstream relationship between the two enterprise objects according to the industrial chain points corresponding to the two enterprise objects when the association similarity between the two enterprise objects is greater than a preset similarity threshold.

[0034] Furthermore, it also includes a building block, and the building block includes:

[0035] The configuration module is used to configure the output layer of the preset neural network prediction model according to a number of industrial chain points in a given industrial chain.

[0036] The third acquisition module is used to input the pre-acquired enterprise information sample set into the preset neural network prediction model for text feature extraction to obtain a number of text feature vectors; the enterprise information sample set includes the name of the enterprise object sample and the product introduction information of the enterprise object sample.

[0037] The fourth acquisition module is used to train a preset neural network prediction model using a number of text feature vectors, and obtain the predicted industrial chain point corresponding to each enterprise object sample from the output layer.

[0038] The parameter adjustment module is used to iteratively adjust the parameters of the preset neural network prediction model according to the predicted industrial chain points and actual industrial chain points corresponding to each enterprise object sample, so as to construct a chain point prediction model.

[0039] Furthermore, the first determining module includes:

[0040] The preprocessing module is used to construct the same number of clusters to be clustered according to the number of enterprise category words, and use the word vector of each enterprise category word as the center of each cluster to be clustered.

[0041] The combination module is used to extract a number of enterprise object keywords from the product introduction information of any enterprise object and form an enterprise keyword group.

[0042] The second determination module is used to calculate the distance between the phrase vector of the enterprise keyword group and each cluster center to be clustered, and determine the target cluster center; the target cluster center refers to the cluster center to be clustered that is closest to the phrase vector of the enterprise keyword group.

[0043] The third determination module is used to determine the enterprise category word corresponding to the target cluster center as the category label of the enterprise object.

[0044] Furthermore, the second acquisition module includes:

[0045] The fourth determination module is used to calculate the TF-IDF value corresponding to each target product keyword, and determine the target product keyword whose corresponding TF-IDF value is greater than a preset TF-IDF threshold as a target product associated word.

[0046] The fifth acquisition module is used to use the trained natural language processing model to acquire product entity words and technical entity words from the target product related words, and use the product entity words and technical entity words as the associated product labels and associated technical labels of the target product respectively.

[0047] Furthermore, the calculation module also includes:

[0048] The sixth acquisition module is used to acquire, for the same cluster center to be clustered, several enterprise keyword groups corresponding to the cluster center to be clustered.

[0049] The mapping module is used to map any enterprise keyword group corresponding to the cluster center to be clustered, and obtain a target distance interval corresponding to the enterprise keyword group from several preset distance intervals according to the distance between the phrase vector of the enterprise keyword group and the cluster center to be clustered.

[0050] The fifth determination module is used to determine the preset weight coefficient corresponding to the target distance interval as the preset weight coefficient corresponding to the enterprise keyword group according to a comparison table of preset distance intervals and preset weight coefficients.

[0051] The seventh acquisition module is used to obtain the preset tag weight corresponding to the category tag according to the preset weight coefficients corresponding to the enterprise keyword groups of the two enterprise objects themselves and the given tag weight corresponding to the category tag when calculating the association similarity between two enterprise objects.

[0052] According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for identifying upstream and downstream relationships of enterprises when executing the computer program.

[0053] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium storing a computer program, which implements the above-mentioned method for identifying upstream and downstream relationships of enterprises when executed by a processor.

[0054] Compared with the prior art, the present invention has at least the following beneficial effects:

[0055] The enterprise upstream and downstream relationship identification method described in the present invention first obtains the industrial chain point corresponding to each enterprise object based on the enterprise information corresponding to a number of enterprise objects and a preset chain point prediction model, then clusters the enterprise objects based on a number of preset enterprise category words, determines the category label of each enterprise object, obtains the associated product label and the associated technical label of the target product according to a number of product description texts in the enterprise object corresponding to any target product, calculates the label similarity corresponding to the three labels between every two enterprise objects, and combines the preset label weights corresponding to the three labels to obtain the associated similarity between the two enterprise objects by weighted sum calculation. When the associated similarity is greater than the preset similarity threshold, the upstream and downstream relationship between the two enterprise objects is identified according to the industrial chain points corresponding to the two enterprise objects. The present invention introduces category labels, associated product labels and associated technical labels that can reflect the production scope of enterprise objects, and can know the industry to which each enterprise object belongs and the related product technology. Through these three labels, the associated similarity between the two enterprise objects is made more reasonable and accurate, thereby making the judgment of the upstream and downstream relationship between the two enterprise objects more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 A flowchart of a method for identifying upstream and downstream relationships of enterprises provided in Embodiment 1 of the present invention;

[0058] Figure 2 A flowchart of the steps of constructing a chain point prediction model provided in the first embodiment of the present invention;

[0059] Figure 3 A flowchart of step S200 provided in Embodiment 1 of the present invention;

[0060] Figure 4 A flowchart of step S300 provided in the first embodiment of the present invention;

[0061] Figure 5 A partial flow chart of step S400 provided in Embodiment 1 of the present invention;

[0062] Figure 6 A schematic diagram of the structure of an enterprise upstream and downstream relationship identification device provided in Embodiment 2 of the present invention;

[0063] Figure 7A schematic diagram of the structure of a building block provided in Embodiment 2 of the present invention;

[0064] Figure 8 A schematic diagram of the structure of a first determination module 200 provided in Embodiment 2 of the present invention;

[0065] Fig. 9 A schematic diagram of the structure of a second acquisition module 300 provided in Embodiment 2 of the present invention;

[0066] Fig.10 A partial structural diagram of a computing module 400 provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0068] Embodiment 1

[0069] like Figure 1 As shown, this embodiment 1 provides a method for identifying upstream and downstream relationships of enterprises, including the following steps:

[0070] S100, based on the enterprise information corresponding to several given enterprise objects and the preset chain point prediction model, obtain the industrial chain chain point corresponding to each enterprise object; the enterprise information corresponding to the enterprise object includes the enterprise object name and the product introduction information of the enterprise object; it can be understood that: the product introduction information of the enterprise object is the names of several business products of the enterprise object.

[0071] In a specific embodiment, Figure 2 As shown, the method constructs the chain point prediction model through the following steps:

[0072] S001, according to a number of industrial chain points in a given industrial chain, configure the output layer of the preset neural network prediction model; it can be understood that: the number of neurons in the output layer is equal to the number of industrial chain points.

[0073] In the specific implementation, a given industrial chain includes several industrial chain points from upstream to downstream: production raw materials, auxiliary materials, production equipment, auxiliary equipment, processing technology, technical services, product business, and sales channels.

[0074] S002, input the pre-acquired enterprise information sample sets into the preset neural network prediction model for text feature extraction, and obtain a number of text feature vectors; the enterprise information sample sets include the names of the enterprise object samples and the product introduction information of the enterprise object samples; it can be understood as: merging the names of the enterprise object samples and the product introduction information of the enterprise object samples corresponding to the same enterprise information sample into one text for feature extraction.

[0075] S003, using a number of text feature vectors to train a preset neural network prediction model, and obtaining the predicted industrial chain point corresponding to each enterprise object sample from the output layer.

[0076] S004, according to the predicted industrial chain points and actual industrial chain points corresponding to each enterprise object sample, iteratively adjust the parameters of the preset neural network prediction model to construct a chain point prediction model.

[0077] As mentioned above, since the enterprise object name and the product introduction information of the enterprise object can well reflect the production scope of the enterprise object, the chain point prediction model is trained by extracting text features of the two, so that the trained chain point prediction model can more accurately predict the production situation of the enterprise object, and then determine the chain point of the industrial chain to which the enterprise object belongs.

[0078] S200, based on a plurality of preset enterprise category words, according to the product introduction information of each enterprise object, a plurality of enterprise objects are clustered to determine the category label of each enterprise object; it can be understood that: the enterprise category words refer to words used to characterize the industry to which the enterprise belongs according to the production scope of the enterprise.

[0079] In a specific embodiment, Figure 3 As shown, step S200 includes the following steps:

[0080] S201, constructing the same number of clusters to be clustered according to the number of enterprise category words, and using the word vector of each enterprise category word as the center of each cluster to be clustered.

[0081] S202, for any enterprise object, extracting a number of enterprise object keywords from the product introduction information of the enterprise object and forming an enterprise keyword group; this can be understood as: extracting a number of enterprise object keywords through a keyword extraction model.

[0082] S203, calculating the distance between the phrase vector of the enterprise keyword group and the center of each cluster to be clustered, and determining the target cluster center; the target cluster center refers to the cluster center to be clustered that is closest to the phrase vector of the enterprise keyword group. For example, the phrase vectors of several enterprise keyword groups are clustered using a k-means clustering model.

[0083] S204: Determine the enterprise category word corresponding to the target cluster center as the category label of the enterprise object.

[0084] As mentioned above, since the product introduction information can reflect the product range produced by the enterprise, several enterprise object keywords are extracted from it and formed into enterprise keyword groups. By clustering the enterprise keyword groups, enterprise objects of the same category can be more accurately clustered into the same cluster, thereby obtaining reliable category labels for the enterprise objects.

[0085] S300, for a target product of any enterprise object, based on a number of product description texts in the enterprise object corresponding to the target product, a number of target product keywords are extracted through a keyword extraction model to obtain associated product tags and associated technical tags of the target product. For example, the product description text may be a patent text or a scientific research project text corresponding to the enterprise object.

[0086] Preferably, the keyword extraction model is a TextRank model, which can accurately extract target product keywords based on the semantic information of the product description text; those skilled in the art are aware of the specific implementation process of extracting keywords using the TextRank model in the prior art, which will not be repeated here.

[0087] In a specific embodiment, Figure 4 As shown, step S300 includes the following steps:

[0088] S301, calculating the TF-IDF value corresponding to each target product keyword, and determining the target product keyword whose corresponding TF-IDF value is greater than a preset TF-IDF threshold as a target product associated word.

[0089] S302, using a trained natural language processing model to obtain product entity words and technical entity words from target product related words, and using the product entity words and technical entity words as related product labels and related technical labels of the target product, respectively.

[0090] Specifically, the natural language processing model is trained based on a preset corpus, wherein the preset corpus includes a number of product entity words and a number of technical entity words; it can be understood as: directly extracted product entity words or product entity words with the same semantics as any preset product entity words are used as associated product labels, and directly extracted technical entity words or technical entity words with the same semantics as any preset technical entity words are used as associated technical labels.

[0091] As mentioned above, by obtaining the associated product tags and associated technology tags of the target product, it is possible to reflect the products or technologies associated with the target product in any enterprise object. Since the upstream and downstream enterprises have overlapping products or technologies, the associated product tags and associated technology tags are used as two associated parameters of the target product, which is conducive to accurately obtaining the association similarity between the two enterprise objects.

[0092] S400, calculate the label similarities corresponding to the category labels, associated product labels and associated technical labels between every two enterprise objects, and weight and calculate the label similarities according to the preset label weights corresponding to the category labels, associated product labels and associated technical labels to obtain the associated similarity between every two enterprise objects.

[0093] In a specific embodiment, Figure 5 As shown, step S400 also includes the following steps:

[0094] S401, for the same cluster center to be clustered, obtain several enterprise keyword groups corresponding to the cluster center to be clustered; it can be understood that: the several enterprise keyword groups corresponding to the cluster center to be clustered refer to several enterprise keyword groups whose corresponding phrase vectors are closest to the cluster center to be clustered.

[0095] S402, for any enterprise keyword group corresponding to the center of the cluster to be clustered, according to the distance between the phrase vector of the enterprise keyword group and the center of the cluster to be clustered, a target distance interval corresponding to the enterprise keyword group is mapped from a plurality of preset distance intervals.

[0096] S403: According to a comparison table of preset distance intervals and preset weight coefficients, the preset weight coefficient corresponding to the target distance interval is determined as the preset weight coefficient corresponding to the enterprise keyword group.

[0097] Specifically, the comparison table of preset distance intervals and preset weight coefficients refers to a data table recording a number of preset distance intervals and a number of preset weight coefficients, and the preset distance intervals and the preset weight coefficients correspond one to one.

[0098] S404, when calculating the association similarity between two enterprise objects, the preset tag weight corresponding to the category tag is obtained according to the preset weight coefficients corresponding to the enterprise keyword groups of the two enterprise objects themselves and the given tag weight corresponding to the category tag.

[0099] As mentioned above, since there will inevitably be certain errors when obtaining the category labels of enterprise objects through clustering, the clustering results are further analyzed, and the accuracy of the category labels is measured according to the distance between the phrase vector of each enterprise keyword group and the center of the corresponding cluster. The closer the distance, the more accurate the clustering result. Therefore, the preset weight coefficient obtained according to the distance is assigned to the given label weight corresponding to the category label, so that the weights assigned to the category labels of the two enterprise objects are more reasonable, thereby improving the accuracy of the similarity calculation.

[0100] S500, when the association similarity between two enterprise objects is greater than a preset similarity threshold, the upstream and downstream relationship between the two enterprise objects is identified according to the industrial chain points corresponding to the two enterprise objects respectively; it can be understood that: when the association similarity between two enterprise objects is greater than a preset similarity threshold, it is determined that the two enterprise objects have an association relationship.

[0101] As mentioned above, after knowing the industrial chain points corresponding to the two enterprise objects, since the two enterprise objects may not belong to the same industry, it is impossible to determine whether the two enterprise objects have an upstream and downstream relationship. By introducing the category label, associated product label and associated technology label of each enterprise object, the association similarity between the two enterprise objects is calculated, so that the calculated association similarity is more accurate and reliable, and then it is known that the two enterprise objects have an association relationship, and the upstream and downstream relationship between the two enterprise objects is determined through the corresponding industrial chain points, which is conducive to subsequent enterprise risk assessment and industry correlation analysis.

[0102] In the prior art, in order to quickly understand the industrial chain information of all-domain products and several enterprise objects, an industrial chain knowledge graph is provided, through which the upstream and downstream relationship between two enterprise objects can be quickly obtained. However, since the data of the industrial chain knowledge graph is not comprehensive enough, it needs to be expanded. Based on this, an embodiment of the present invention also provides an industrial chain knowledge graph expansion method, which includes the following steps:

[0103] P100, for a given product of an enterprise object, a number of first product keywords are extracted through a keyword extraction model according to a number of product description texts in the enterprise object corresponding to the given product.

[0104] Furthermore, the step of extracting a plurality of first product keywords through the keyword extraction model further includes the following steps:

[0105] P101, when the number of first product keywords extracted from a plurality of product description texts is greater than a preset number threshold, a preset grammar filter is used to filter the plurality of first product keywords to obtain a new keyword vertex set.

[0106] P102, determining a plurality of first product keywords in the new keyword vertex set as a plurality of first product keywords finally extracted.

[0107] As mentioned above, when the number of extracted first product keywords is large, the first product keywords with low importance can be screened out through the processing of the preset grammar filter, thereby achieving the optimization of the first product keyword set. By extracting a number of first product keywords, it is beneficial to subsequently obtain a number of target texts related to a given product.

[0108] P200, based on the TF-IDF value corresponding to each first product keyword and the preset TF-IDF threshold, select a number of second product keywords from a number of first product keywords, and obtain a number of target texts corresponding to the number of second product keywords from a preset text library; it can be understood as: the first product keyword whose corresponding TF-IDF value is greater than the preset TF-IDF threshold is determined as the second product keyword.

[0109] In a specific embodiment, the target text is obtained in step P200 through the following steps:

[0110] P201, obtain a number of first texts to be processed corresponding to each second product keyword from a preset text library, and determine a number of target sentences from each first text to be processed; the target sentence refers to a sentence including at least one second product keyword obtained from a target paragraph in any first text to be processed.

[0111] In a specific embodiment, in step P201, the target paragraph in the first to-be-processed text is determined by the following steps:

[0112] P2011, obtain from the preset text library a number of first texts to be processed corresponding to each second product keyword and a text category identifier of each first text to be processed; it can be understood as: obtaining a text containing at least one second product keyword from the preset text library as the first text to be processed.

[0113] Specifically, the text category identification includes but is not limited to patent text and paper text.

[0114] P2012, for any first text to be processed, determine the target paragraph from the first text to be processed based on the correspondence between the preset text category identifier and the target paragraph in the first text to be processed; for example, when the text category identifier is a patent text, considering the repetitiveness of words, the specific implementation method part is taken as the target paragraph.

[0115] In the above, by obtaining the first text to be processed based on several second product keywords, the obtained related text is made more comprehensive, and then the target sentence containing the second product keywords is further determined from the target paragraph of the first text to be processed, so that the number of each second product keyword in the obtained target sentence can provide a basis for calculating the text priority of the first text to be processed.

[0116] P202, for any first text to be processed, according to the quantity information of each second product keyword in each target sentence in the first text to be processed, obtain the first text priority corresponding to the first text to be processed.

[0117] Specifically, the first text priority corresponding to the first to-be-processed text is obtained through the following steps:

[0118] P2021, for any target sentence in the first text to be processed, divide the several second product keywords in the target sentence into several target phrases; the target phrase refers to any phrase in which the number of second product keywords screened out among the currently remaining several second product keywords is the largest and each screened out second product keyword has only one; the currently remaining several second product keywords refer to the remaining several second product keywords obtained after deleting all the screened out second product keywords from the several second product keywords in the target sentence.

[0119] For a better understanding, an example is given below: when the second product keywords in the target sentence include A1, A2, A3, A2, A1, A1, A1, A1, the first screening obtains the target phrase (A1, A2, A3), the remaining second product keywords currently include A2, A1, A1, A1, the second screening obtains the target phrase (A1, A2), the remaining second product keywords currently include A1, A1, the third screening obtains the target phrase (A1), the remaining second product keywords currently are A1, so the last screening obtains the target phrase (A1).

[0120] P2022, for any target phrase corresponding to the target sentence, calculate the first phrase priority corresponding to the target phrase based on the total number of second product keywords in the target phrase and the target number corresponding to the target phrase; the target number corresponding to the target phrase refers to the number of phrases that are identical to any target phrase obtained from several target phrases corresponding to the target sentence.

[0121] Further, the first phrase priority corresponding to the target phrase is the product of the total number of second product keywords in the target phrase and the target number corresponding to the target phrase.

[0122] For example, when the target phrase is (A1, A2, A3), the total number of second product keywords in the target phrase is 3, the target number corresponding to the target phrase is 1, and the priority of the first phrase corresponding to the target phrase is 3; when the target phrase is (A1), the total number of second product keywords in the target phrase is 1, the target number corresponding to the target phrase is 2, and the priority of the first phrase corresponding to the target phrase is 2.

[0123] P2023, based on the same target phrase information in several target phrases corresponding to the target sentence, several first phrase priorities are deduplicated to obtain several second phrase priorities; it can be understood as: the target phrases are deduplicated, and the first phrase priorities corresponding to the removed target phrases are also removed, because when calculating the first phrase priority of the target phrase, all target phrases that are the same as the target phrase have been taken into account.

[0124] P2024, the sum of the priorities of the second phrases is determined as the sentence priority corresponding to the target sentence.

[0125] P2025, add up the sentence priorities corresponding to several target sentences in the first text to be processed, and obtain the first text priority corresponding to the first text to be processed.

[0126] As described above, when calculating the first text priority of the first text to be processed, the dimension of the second product keywords contained in the first text to be processed is considered. By introducing the combination of the second product keywords and the number of each combination, the importance of the first text to be processed can be more accurately reflected.

[0127] P203, obtain several second texts to be processed corresponding to the first text to be processed, and obtain the second text priority corresponding to the first text to be processed based on several second product keywords corresponding to each second text to be processed and the length of time between the first text to be processed and the publication time of each second text to be processed.

[0128] Specifically, the second text to be processed refers to any first text to be processed whose publication time is earlier than that of the first text to be processed.

[0129] Specifically, the second text priority corresponding to the first to-be-processed text is obtained through the following steps:

[0130] P2031, according to the time between the publication time of the first text to be processed and the publication time of each second text to be processed, normalize each time to obtain the time proportion parameter corresponding to each second text to be processed.

[0131] P2032, for any second text to be processed, according to the second product keywords corresponding to the second text to be processed, obtain the number of second product keywords repeated between the second text to be processed and the first text to be processed. For example, the first text to be processed includes the second product keywords A1, A2, A3, and the second text to be processed includes the second product keywords A1 and A2, then the total number of repeated second product keywords is 2.

[0132] P2033, determine the text weight of the second text to be processed by multiplying the time proportion parameter corresponding to the second text to be processed and the total number of second product keywords repeated between the second text to be processed and the first text to be processed.

[0133] P2034, calculate the ratio of the sum of the text weights of each second text to be processed to the number of second texts to be processed, and use the calculation result as the second text priority corresponding to the first text to be processed.

[0134] As described above, when calculating the second text priority of the first text to be processed, the dimension of several second texts to be processed whose publication time is before the first text to be processed is taken into consideration, and the time dimension is also introduced into the number of repeated words as the weight of the number of repeated words, which can accurately reflect the importance of each second text to be processed to the first text to be processed, thereby improving the reliability of the second text priority corresponding to the first text to be processed.

[0135] P204, when the sum of the first text priority and the second text priority corresponding to the first text to be processed is greater than a preset priority threshold, the first text to be processed is used as the target text.

[0136] As described above, the priority of the text is considered through multiple dimensions, which makes the determination of the target text with high relevance to the second product keyword more reasonable and reliable, and the several target texts with different disclosure times that are finally determined are helpful to reflect the development progress of the product to a certain extent, making the extraction of the third product keyword more comprehensive.

[0137] P300, extracts several third product keywords from several target texts, and generates feature vectors to input into the target neural network prediction model, obtains the target category label corresponding to the given product, and obtains the target industrial chain corresponding to the enterprise object according to the preset industrial chain mapping table; the industrial chain mapping table includes several groups of one-to-one corresponding enterprise category words and preset industrial chains.

[0138] In a specific embodiment, the target neural network prediction model is obtained by the following steps:

[0139] P10, according to the number of enterprise category words, the neurons of the output layer of the preset neural network prediction model are configured; it can be understood that: the number of neurons in the output layer is equal to the number of enterprise category words.

[0140] P20, obtaining a number of historical products under each enterprise category word and a number of historical texts corresponding to each historical product; the method for obtaining the historical texts is consistent with the method for obtaining the target text.

[0141] P30, for any historical product under any enterprise category word, extract several historical product keywords from several historical texts corresponding to the historical product, and input the several historical product keywords into the preset neural network prediction model for feature extraction to obtain a text feature vector; it can be understood as: merging several historical product keywords into one text for feature extraction.

[0142] P40, uses several text feature vectors to train the preset neural network prediction model, and obtains the target category label corresponding to each historical product from the output layer.

[0143] P50, according to the target category label corresponding to each historical product and the enterprise category word corresponding to each historical product, the preset neural network prediction model is iteratively adjusted to construct a target neural network prediction model.

[0144] As described above, through historical products of different categories and several historical texts corresponding to each historical product, a large number of text features are extracted to train the preset neural network prediction model, so that the trained target neural network prediction model can accurately and reliably predict the category to which the product belongs.

[0145] P400, calculating the keyword similarity between any second product keyword and each third product keyword, and when there is a keyword similarity greater than a preset similarity threshold, determining that the second product keyword itself and the corresponding third product keyword have a matching relationship.

[0146] Specifically, the keyword similarity between any second product keyword and any third product keyword meets the following conditions:

[0147] ζ=(α·β) / (||α||×||β||), where ζ is the keyword similarity between any second product keyword and any third product keyword, α is the word vector corresponding to any second product keyword, and β is the word vector corresponding to any third product keyword.

[0148] As mentioned above, since the second product keyword and the third product keyword are not exactly the same, they may also represent the same object or have the same semantics, so the keyword similarity between the two is calculated. When the keyword similarity is large, it is considered that there is a matching relationship, which makes the judgment of the overlapping amount of the second product keyword and the third product keyword more accurate, thereby providing a judgment basis for determining whether the target industrial chain is the industrial chain corresponding to a given product.

[0149] P500, when the ratio of the number of second product keywords with matching relationships to the total number of second product keywords is greater than the preset ratio threshold, the enterprise object, the given product and the target chain point are fused and linked according to the target chain point corresponding to the given product in the target industrial chain, so as to realize the expansion of the industrial chain knowledge graph.

[0150] As mentioned above, when the ratio of the number of second product keywords with matching relationships to the total number of second product keywords is large, it indicates that the number of identical or similar second product keywords and third product keywords is relatively large, and the acquired target industrial chain can be reasonably determined as the industrial chain corresponding to the given product. At this time, the enterprise object, the given product and the target chain point in the target industrial chain are integrated and connected, which can realize the accurate and reliable expansion of the industrial chain knowledge graph, and then help the enterprise object to understand the full range of products and other enterprise objects, so as to facilitate the subsequent enterprise risk assessment and industry correlation analysis.

[0151] In a specific embodiment, the target chain point corresponding to a given product in the target industrial chain is determined by the following steps:

[0152] P001, obtain the names of each industrial chain point in the target industrial chain.

[0153] P002, use NLP model to perform semantic analysis on several product description texts, determine the semantic text similarity between any product description text and each industrial chain link name, and determine the maximum semantic text similarity corresponding to any product description text. For example, when there are eight industrial chain link names, one product description text corresponds to eight semantic text similarities, and the maximum value among them is taken as the maximum semantic text similarity corresponding to the product description text; the NLP model obtains semantic text similarity is a prior art and will not be repeated here.

[0154] P003, the industrial chain point with the largest number of corresponding maximum semantic text similarities is determined as the target link point corresponding to the given product in the target industrial chain.

[0155] In the above, by analyzing the semantic text similarities between several product description texts corresponding to the same product and each industrial chain point, and according to the number of maximum semantic text similarities corresponding to the industrial chain points, the target chain point corresponding to a given product is determined, so that the obtained target chain point is more accurate and reliable.

[0156] Embodiment 2

[0157] like Figure 6 As shown, this embodiment 2 provides a device for identifying upstream and downstream relationships of enterprises, including:

[0158] The first acquisition module 100 is used to obtain the industrial chain chain points corresponding to each enterprise object based on the enterprise information corresponding to a given number of enterprise objects and a preset chain point prediction model; the enterprise information corresponding to the enterprise object includes the enterprise object name and the product introduction information of the enterprise object; it can be understood that the product introduction information of the enterprise object is the names of several business products of the enterprise object.

[0159] In a specific embodiment, Figure 7 As shown, the device also includes a building module, and the building module includes:

[0160] Configuration module 001 is used to configure the output layer of the preset neural network prediction model according to a number of industrial chain points in a given industrial chain; it can be understood that: the number of neurons in the output layer is equal to the number of industrial chain points.

[0161] In the specific implementation, a given industrial chain includes several industrial chain points from upstream to downstream: production raw materials, auxiliary materials, production equipment, auxiliary equipment, processing technology, technical services, product business, and sales channels.

[0162] The third acquisition module 002 is used to input the pre-acquired enterprise information sample sets into the preset neural network prediction model for text feature extraction, and obtain a number of text feature vectors; the enterprise information sample sets include the names of the enterprise object samples and the product introduction information of the enterprise object samples; it can be understood as: the names of the enterprise object samples and the product introduction information of the enterprise object samples corresponding to the same enterprise information sample are merged into one text for feature extraction.

[0163] The fourth acquisition module 003 is used to train a preset neural network prediction model using a number of text feature vectors, and obtain the predicted industrial chain point corresponding to each enterprise object sample from the output layer.

[0164] The parameter adjustment module 004 is used to iteratively adjust the parameters of the preset neural network prediction model according to the predicted industrial chain points and actual industrial chain points corresponding to each enterprise object sample, so as to construct a chain point prediction model.

[0165] As mentioned above, since the enterprise object name and the product introduction information of the enterprise object can well reflect the production scope of the enterprise object, the chain point prediction model is trained by extracting text features of the two, so that the trained chain point prediction model can more accurately predict the production situation of the enterprise object, and then determine the chain point of the industrial chain to which the enterprise object belongs.

[0166] The first determination module 200 is used to cluster a number of enterprise objects based on a number of preset enterprise category words and according to the product introduction information of each enterprise object, and determine the category label of each enterprise object; it can be understood that: the enterprise category word refers to a word used to characterize the industry to which the enterprise belongs based on the production scope of the enterprise.

[0167] In a specific embodiment, Figure 8 As shown, the first determining module 200 includes:

[0168] The preprocessing module 201 is used to construct the same number of clusters to be clustered according to the number of enterprise category words, and use the word vector of each enterprise category word as the center of each cluster to be clustered.

[0169] The combination module 202 is used to extract a number of enterprise object keywords from the product introduction information of any enterprise object and form an enterprise keyword group; it can be understood as: extracting a number of enterprise object keywords through a keyword extraction model.

[0170] The second determination module 203 is used to calculate the distance between the phrase vector of the enterprise keyword group and each cluster center to be clustered, and determine the target cluster center; the target cluster center refers to the cluster center to be clustered that is closest to the phrase vector of the enterprise keyword group. For example, the phrase vectors of several enterprise keyword groups are clustered using a k-means clustering model.

[0171] The third determination module 204 is used to determine the enterprise category word corresponding to the target cluster center as the category label of the enterprise object.

[0172] As mentioned above, since the product introduction information can reflect the product range produced by the enterprise, several enterprise object keywords are extracted from it and formed into enterprise keyword groups. By clustering the enterprise keyword groups, enterprise objects of the same category can be more accurately clustered into the same cluster, thereby obtaining reliable category labels for the enterprise objects.

[0173] The second acquisition module 300 is used to extract a number of target product keywords from a number of product description texts in the enterprise object corresponding to the target product through a keyword extraction model for a target product of any enterprise object, so as to obtain the associated product tags and associated technical tags of the target product. For example, the product description text may be a patent text or a scientific research project text corresponding to the enterprise object.

[0174] Preferably, the keyword extraction model is a TextRank model, which can accurately extract target product keywords based on the semantic information of the product description text; those skilled in the art are aware of the specific implementation process of extracting keywords using the TextRank model in the prior art, which will not be repeated here.

[0175] In a specific embodiment, Fig. 9 As shown, the second acquisition module 300 includes:

[0176] The fourth determination module 301 is used to calculate the TF-IDF value corresponding to each target product keyword, and determine the target product keyword whose corresponding TF-IDF value is greater than a preset TF-IDF threshold as a target product associated word.

[0177] The fifth acquisition module 302 is used to use the trained natural language processing model to acquire product entity words and technical entity words from the target product related words, and use the product entity words and technical entity words as the related product labels and related technical labels of the target product respectively.

[0178] Specifically, the natural language processing model is trained based on a preset corpus, wherein the preset corpus includes a number of product entity words and a number of technical entity words; it can be understood as: directly extracted product entity words or product entity words with the same semantics as any preset product entity words are used as associated product labels, and directly extracted technical entity words or technical entity words with the same semantics as any preset technical entity words are used as associated technical labels.

[0179] As described above, by obtaining the associated product tags and associated technology tags of the target product, it is possible to reflect the products or technologies associated with the target product in any enterprise object. Using the associated product tags and associated technology tags as two associated parameters of the target product is conducive to obtaining the association similarity between the two enterprise objects.

[0180] The calculation module 400 is used to calculate the label similarities corresponding to the category labels, associated product labels and associated technical labels between every two enterprise objects, and to weight and calculate the label similarities according to the preset label weights corresponding to the category labels, associated product labels and associated technical labels to obtain the associated similarity between every two enterprise objects.

[0181] In a specific embodiment, Fig.10 As shown, the calculation module 400 also includes:

[0182] The sixth acquisition module 401 is used to acquire several enterprise keyword groups corresponding to the same cluster center to be clustered; it can be understood that: the several enterprise keyword groups corresponding to the cluster center to be clustered refer to several enterprise keyword groups whose corresponding phrase vectors are closest to the cluster center to be clustered.

[0183] The mapping module 402 is used to map any enterprise keyword group corresponding to the cluster center to obtain a target distance interval corresponding to the enterprise keyword group from a number of preset distance intervals according to the distance between the phrase vector of the enterprise keyword group and the cluster center to be clustered.

[0184] The fifth determination module 403 is used to determine the preset weight coefficient corresponding to the target distance interval as the preset weight coefficient corresponding to the enterprise keyword group according to a comparison table of preset distance intervals and preset weight coefficients.

[0185] Specifically, the comparison table of preset distance intervals and preset weight coefficients refers to a data table recording a number of preset distance intervals and a number of preset weight coefficients, and the preset distance intervals and the preset weight coefficients correspond one to one.

[0186] The seventh acquisition module 404 is used to acquire the preset tag weight corresponding to the category tag according to the preset weight coefficients corresponding to the enterprise keyword groups of the two enterprise objects themselves and the given tag weight corresponding to the category tag when calculating the association similarity between the two enterprise objects.

[0187] As mentioned above, since there will inevitably be certain errors when obtaining the category labels of enterprise objects through clustering, the clustering results are further analyzed, and the accuracy of the category labels is measured according to the distance between the phrase vector of each enterprise keyword group and the center of the corresponding cluster. The closer the distance, the more accurate the clustering result. Therefore, the preset weight coefficient obtained according to the distance is assigned to the given label weight corresponding to the category label, so that the weights assigned to the category labels of the two enterprise objects are more reasonable, thereby improving the accuracy of the similarity calculation.

[0188] The identification module 500 is used to identify the upstream and downstream relationship between the two enterprise objects according to the industrial chain points corresponding to the two enterprise objects when the association similarity between the two enterprise objects is greater than the preset similarity threshold. It can be understood that: when the association similarity between the two enterprise objects is greater than the preset similarity threshold, it is determined that the two enterprise objects have an association relationship.

[0189] As mentioned above, after knowing the industrial chain points corresponding to the two enterprise objects, since the two enterprise objects may not belong to the same industry, it is impossible to determine whether the two enterprise objects have an upstream and downstream relationship. By introducing the category label, associated product label and associated technology label of each enterprise object, the association similarity between the two enterprise objects is calculated, so that the calculated association similarity is more accurate and reliable, and then it is known that the two enterprise objects have an association relationship, and the upstream and downstream relationship between the two enterprise objects is determined through the corresponding industrial chain points, which is conducive to subsequent enterprise risk assessment and industry correlation analysis.

[0190] Embodiment 3

[0191] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented:

[0192] According to the enterprise information corresponding to a given number of enterprise objects and a preset chain point prediction model, the industrial chain chain point corresponding to each enterprise object is obtained; the enterprise information corresponding to the enterprise object includes the enterprise object name and the product introduction information of the enterprise object.

[0193] Based on a number of preset enterprise category words and according to the product introduction information of each enterprise object, a number of enterprise objects are clustered to determine the category label of each enterprise object.

[0194] For the target product of any enterprise object, several target product keywords are extracted through the keyword extraction model according to several product description texts in the enterprise object corresponding to the target product, so as to obtain the associated product tags and associated technical tags of the target product.

[0195] The label similarities corresponding to the category labels, associated product labels and associated technical labels between every two enterprise objects are calculated, and the label similarities are weighted and calculated according to the preset label weights corresponding to the category labels, associated product labels and associated technical labels to obtain the association similarity between every two enterprise objects.

[0196] When the association similarity between two enterprise objects is greater than a preset similarity threshold, the upstream and downstream relationship between the two enterprise objects is identified according to the industrial chain points corresponding to the two enterprise objects.

[0197] Embodiment 4

[0198] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0199] According to the enterprise information corresponding to a given number of enterprise objects and a preset chain point prediction model, the industrial chain chain point corresponding to each enterprise object is obtained; the enterprise information corresponding to the enterprise object includes the enterprise object name and the product introduction information of the enterprise object.

[0200] Based on a number of preset enterprise category words and according to the product introduction information of each enterprise object, a number of enterprise objects are clustered to determine the category label of each enterprise object.

[0201] For the target product of any enterprise object, several target product keywords are extracted through the keyword extraction model according to several product description texts in the enterprise object corresponding to the target product, so as to obtain the associated product tags and associated technical tags of the target product.

[0202] The label similarities corresponding to the category labels, associated product labels and associated technical labels between every two enterprise objects are calculated, and the label similarities are weighted and calculated according to the preset label weights corresponding to the category labels, associated product labels and associated technical labels to obtain the association similarity between every two enterprise objects.

[0203] When the association similarity between two enterprise objects is greater than a preset similarity threshold, the upstream and downstream relationship between the two enterprise objects is identified according to the industrial chain points corresponding to the two enterprise objects.

[0204] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0205] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0206] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for identifying upstream and downstream relationships of enterprises, characterized in that: The following steps are involved: According to the enterprise information corresponding to a number of given enterprise objects and a preset chain point prediction model, the industrial chain chain point corresponding to each enterprise object is obtained; the enterprise information corresponding to the enterprise object includes the enterprise object name and the product introduction information of the enterprise object; Based on a number of preset enterprise category words, a number of enterprise objects are clustered according to the product introduction information of each enterprise object to determine the category label of each enterprise object; For a target product of any enterprise object, based on a number of product description texts in the enterprise object corresponding to the target product, a number of target product keywords are extracted through a keyword extraction model to obtain associated product tags and associated technical tags of the target product; Calculate the label similarities corresponding to the category labels, associated product labels, and associated technical labels between every two enterprise objects, and weight and calculate the label similarities according to the preset label weights corresponding to the category labels, associated product labels, and associated technical labels to obtain the association similarity between every two enterprise objects; When the association similarity between two enterprise objects is greater than a preset similarity threshold, the upstream and downstream relationship between the two enterprise objects is identified according to the industrial chain points corresponding to the two enterprise objects respectively; The category label of the enterprise object is determined through the following steps: According to the number of enterprise category words, the same number of clusters to be clustered are constructed, and the word vector of each enterprise category word is used as the center of each cluster to be clustered; For any enterprise object, extract several enterprise object keywords from the product introduction information of the enterprise object and form an enterprise keyword group; Calculate the distance between the phrase vector of the enterprise keyword group and each cluster center to be clustered, and determine the target cluster center; the target cluster center refers to the cluster center to be clustered that is closest to the phrase vector of the enterprise keyword group; Determine the enterprise category word corresponding to the target cluster center as the category label of the enterprise object; The preset label weights corresponding to the category labels are also obtained through the following steps: For the same cluster center to be clustered, obtain several enterprise keyword groups corresponding to the cluster center to be clustered; For any enterprise keyword group corresponding to the center of the cluster to be clustered, according to the distance between the phrase vector of the enterprise keyword group and the center of the cluster to be clustered, a target distance interval corresponding to the enterprise keyword group is mapped from a number of preset distance intervals; According to the comparison table of preset distance intervals and preset weight coefficients, the preset weight coefficient corresponding to the target distance interval is determined as the preset weight coefficient corresponding to the enterprise keyword group; When calculating the association similarity between two enterprise objects, the preset tag weight corresponding to the category tag is obtained according to the preset weight coefficients corresponding to the enterprise keyword groups of the two enterprise objects themselves and the given tag weight corresponding to the category tag.

2. The method for identifying upstream and downstream relationships of enterprises according to claim 1, characterized in that: The chain point prediction model is constructed by the following steps: According to a number of industrial chain points in a given industrial chain, the output layer of the preset neural network prediction model is configured; Inputting the pre-acquired enterprise information sample sets into the preset neural network prediction model to extract text features, and obtaining a number of text feature vectors; the enterprise information sample sets include the names of enterprise object samples and product introduction information of enterprise object samples; Use several text feature vectors to train the preset neural network prediction model, and obtain the predicted industrial chain point corresponding to each enterprise object sample from the output layer; According to the predicted industrial chain points and actual industrial chain points corresponding to each enterprise object sample, the preset neural network prediction model is iteratively adjusted to construct a chain point prediction model.

3. The method for identifying upstream and downstream relationships of enterprises according to claim 1, characterized in that: Obtain the associated product tags and associated technology tags of the target product through the following steps: Calculate the TF-IDF value corresponding to each target product keyword, and determine the target product keyword whose corresponding TF-IDF value is greater than a preset TF-IDF threshold as a target product associated word; The trained natural language processing model is used to obtain product entity words and technical entity words from the target product related words, and the product entity words and technical entity words are used as the associated product labels and associated technology labels of the target product respectively.

4. A device for identifying upstream and downstream relationships of enterprises, characterized in that: The device comprises: The first acquisition module is used to acquire the industrial chain link point corresponding to each enterprise object according to the enterprise information corresponding to a given number of enterprise objects and a preset link point prediction model; the enterprise information corresponding to the enterprise object includes the enterprise object name and the product introduction information of the enterprise object; A first determination module is used to cluster a number of enterprise objects based on a number of preset enterprise category words and according to the product introduction information of each enterprise object, and determine a category label for each enterprise object; The second acquisition module is used to extract a number of target product keywords through a keyword extraction model for a target product of any enterprise object according to a number of product description texts in the enterprise object corresponding to the target product, so as to obtain the associated product tags and associated technical tags of the target product; A calculation module, used to calculate the label similarities corresponding to the category labels, associated product labels and associated technical labels between every two enterprise objects, and to weight and calculate the label similarities according to the preset label weights corresponding to the category labels, associated product labels and associated technical labels to obtain the association similarity between every two enterprise objects; An identification module, used to identify the upstream and downstream relationship between the two enterprise objects according to the industrial chain points corresponding to the two enterprise objects when the association similarity between the two enterprise objects is greater than a preset similarity threshold; Wherein, the first determining module includes: A preprocessing module is used to construct the same number of clusters to be clustered according to the number of enterprise category words, and use the word vector of each enterprise category word as the center of each cluster to be clustered; A combination module is used to extract a number of enterprise object keywords from the product introduction information of any enterprise object and form an enterprise keyword group; The second determination module is used to calculate the distance between the phrase vector of the enterprise keyword group and each cluster center to be clustered, and determine the target cluster center; the target cluster center refers to the cluster center to be clustered that is closest to the phrase vector of the enterprise keyword group; A third determination module is used to determine the enterprise category word corresponding to the target cluster center as the category label of the enterprise object; The calculation module also includes: A sixth acquisition module is used to acquire, for the same cluster center to be clustered, a number of enterprise keyword groups corresponding to the cluster center to be clustered; A mapping module, for mapping any enterprise keyword group corresponding to the center of the cluster to be clustered, according to the distance between the phrase vector of the enterprise keyword group and the center of the cluster to be clustered, to obtain a target distance interval corresponding to the enterprise keyword group from a plurality of preset distance intervals; A fifth determination module, for determining the preset weight coefficient corresponding to the target distance interval as the preset weight coefficient corresponding to the enterprise keyword group according to a comparison table of preset distance intervals and preset weight coefficients; The seventh acquisition module is used to obtain the preset tag weight corresponding to the category tag according to the preset weight coefficients corresponding to the enterprise keyword groups of the two enterprise objects themselves and the given tag weight corresponding to the category tag when calculating the association similarity between two enterprise objects.

5. The device for identifying upstream and downstream relationships of enterprises according to claim 4, characterized in that: Also included are building blocks, the building blocks comprising: A configuration module, used to configure the output layer of a preset neural network prediction model according to a number of industrial chain points in a given industrial chain; The third acquisition module is used to input the pre-acquired enterprise information sample set into the preset neural network prediction model to extract text features and obtain a number of text feature vectors; the enterprise information sample set includes the name of the enterprise object sample and the product introduction information of the enterprise object sample; The fourth acquisition module is used to train the preset neural network prediction model using a number of text feature vectors, and obtain the predicted industrial chain point corresponding to each enterprise object sample from the output layer; The parameter adjustment module is used to iteratively adjust the parameters of the preset neural network prediction model according to the predicted industrial chain points and actual industrial chain points corresponding to each enterprise object sample, so as to construct a chain point prediction model.

6. The device for identifying upstream and downstream relationships of enterprises according to claim 4, characterized in that: The second acquisition module includes: A fourth determination module is used to calculate the TF-IDF value corresponding to each target product keyword, and determine the target product keyword whose corresponding TF-IDF value is greater than a preset TF-IDF threshold as a target product associated word; The fifth acquisition module is used to use the trained natural language processing model to acquire product entity words and technical entity words from the target product related words, and use the product entity words and technical entity words as the associated product labels and associated technical labels of the target product respectively.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for identifying upstream and downstream relationships of enterprises as described in any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for identifying upstream and downstream relationships of enterprises as described in any one of claims 1 to 3 is implemented.

Images