Data determination method, storage medium, program product and processor

Abstract

The present application discloses a method for determining data, a storage medium, a program product, and a processor. The method includes: obtaining a to-be-processed chapter of a target object; determining a first feature vector set corresponding to the to-be-processed chapter, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or the attribute information corresponding to the to-be-processed chapter; using the first feature vector set, determining at least one second feature vector set associated with the to-be-processed chapter from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determining at least one associated chapter associated with the to-be-processed chapter; based on the behavior information of the target object, determining a to-be-recommended chapter from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object. The present application solves the technical problem of low data processing efficiency.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a data determination method, a storage medium, a program product, and a processor. Background Art

[0002] At present, the traditional preparation of reports is usually only based on the attributes of the chapters in the report to the corresponding business units and departments, and the business personnel provide the chapter information in the report according to the report format guidance requirements. However, the above processing of chapters in the report is usually just manual processing of the chapters. During the processing, the labor cost is high, the coverage iteration is slow, and there are technical problems such as low data processing efficiency.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a data determination method, a storage medium, a program product, and a processor to at least solve the technical problem of low data processing efficiency.

[0005] According to one aspect of an embodiment of the present application, a method for determining data is provided, which may include: acquiring a to-be-processed chapter of a target object; determining a first feature vector set corresponding to the to-be-processed chapter, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or the attribute information corresponding to the to-be-processed chapter; using the first feature vector set, determining at least one second feature vector set associated with the to-be-processed chapter from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determining at least one associated chapter associated with the to-be-processed chapter; based on the behavior information of the target object, determining a to-be-recommended chapter from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object.

[0006] Optionally, based on the second feature vector set, at least one associated chapter associated with the chapter to be processed is determined, including: determining a first matching degree between the second feature vector set and the first feature vector set; in response to the first matching degree being greater than a matching degree threshold, determining the historical chapter corresponding to the second feature vector set as the target chapter; obtaining a first association rule associated with the target chapter, wherein the first association rule is used to characterize the association relationship between multiple historical chapters; and determining at least one associated chapter from the database according to the first association rule.

[0007] Optionally, based on the second feature vector set, at least one associated chapter associated with the chapter to be processed is determined, including: determining at least one frequent vector from multiple second feature vector sets, wherein the frequent vector is used to represent a subvector in the second feature vector set whose number of appearances is greater than a number threshold; constructing a second association rule associated with the frequent vector, and respectively determining a second matching degree between at least one frequent vector and the first feature vector set, wherein the second association rule is used to represent the association relationship between the frequent vector and at least one historical chapter; in response to the second matching degree being greater than the matching degree threshold, determining at least one associated chapter from the historical chapters according to the second association rule associated with the frequent vector.

[0008] Optionally, the method may further include: receiving multiple historical reports from multiple information collection channels, wherein the historical reports include at least one historical chapter; preprocessing the historical chapter; performing feature extraction on the preprocessed historical chapter to obtain a set of historical feature vectors corresponding to the preprocessed historical chapter.

[0009] Optionally, feature extraction is performed on the preprocessed historical chapters to obtain a historical feature vector set corresponding to the preprocessed historical chapters, including: segmenting the text in the historical chapters to obtain multiple sub-texts; and constructing a historical feature vector set based on the occurrence frequency of the sub-texts.

[0010] Optionally, based on the behavior information of the target object, a chapter to be recommended is determined from at least one associated chapter, including: determining the target object's preference for the associated chapter based on the behavior information; in response to the preference degree being greater than a preference threshold, determining the associated chapter as a chapter to be recommended; in response to the preference degree being less than or equal to the preference threshold, determining the associated chapter as a non-chapter to be recommended.

[0011] According to another aspect of an embodiment of the present application, another method for determining data is provided, which may include: obtaining a to-be-processed chapter of a target object; determining a first feature vector set corresponding to the to-be-processed chapter, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or the attribute information corresponding to the to-be-processed chapter; using the first feature vector set, determining at least one second feature vector set associated with the to-be-processed chapter from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determining at least one associated chapter associated with the to-be-processed chapter; respectively determining the degree of association between at least one associated chapter and the to-be-processed chapter; and determining a to-be-recommended chapter from at least one associated chapter based on the degree of association.

[0012] According to another aspect of an embodiment of the present application, a data determination device is also provided, which may include: a first acquisition unit, used to acquire a to-be-processed chapter of a target object; a first determination unit, used to determine a first feature vector set corresponding to the to-be-processed chapter, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or the attribute information corresponding to the to-be-processed chapter; a second determination unit, used to determine, using the first feature vector set, at least one second feature vector set associated with the to-be-processed chapter from a plurality of historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; a third determination unit, used to determine, based on the second feature vector set, at least one associated chapter associated with the to-be-processed chapter; and a fourth determination unit, used to determine, from at least one associated chapter, a chapter to be recommended based on the behavior information of the target object, wherein the behavior information is used to characterize the chapter preference of the target object.

[0013] According to another aspect of an embodiment of the present application, another data determination device is also provided, which may include: a second acquisition unit, used to acquire a to-be-processed chapter of a target object; a fifth determination unit, used to determine a first feature vector set corresponding to the to-be-processed chapter, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or the attribute information corresponding to the to-be-processed chapter; a sixth determination unit, used to determine, using the first feature vector set, at least one second feature vector set associated with the to-be-processed chapter from a plurality of historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; a seventh determination unit, used to determine, based on the second feature vector set, at least one associated chapter associated with the to-be-processed chapter; an eighth determination unit, used to respectively determine the degree of association between at least one associated chapter and the to-be-processed chapter; and a ninth determination unit, used to determine a to-be-recommended chapter in at least one associated chapter based on the degree of association.

[0014] According to another aspect of an embodiment of the present application, a computer-readable storage medium is further provided, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the data determination method of the embodiment of the present application.

[0015] According to another aspect of an embodiment of the present application, a processor is further provided, the processor being used to run a program, wherein the program, when run by the processor, executes the method for determining data of an embodiment of the present application.

[0016] According to another aspect of an embodiment of the present application, a computer program product is further provided. The computer program product includes computer instructions, wherein the computer instructions, when executed by a processor, implement the data determination method of the embodiment of the present application.

[0017] In an embodiment of the present application, a chapter to be processed of a target object is obtained; a first feature vector set corresponding to the chapter to be processed is determined, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; using the first feature vector set, at least one second feature vector set associated with the chapter to be processed is determined from multiple historical feature vector sets, wherein the second feature vector set is used to characterize at least the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, at least one associated chapter associated with the chapter to be processed is determined; based on the behavior information of the target object, a chapter to be recommended is determined from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object. That is, in an embodiment of the present application, based on the first feature vector set of the chapter to be processed in the report, at least one associated chapter associated with the chapter to be processed is determined from multiple historical chapters, and further, based on the behavior information of the target object, a chapter to be recommended in at least one associated chapter can be determined, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a flow chart of a method for determining data according to an embodiment of the present application;

[0020] Figure 2 is a flow chart of another method for determining data according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a data determination device according to an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of another data determination device according to an embodiment of the present application;

[0023] Figure 5 is a structural block diagram of a computer terminal according to an embodiment of the present application;

[0024] Figure 6 The present invention is a block diagram of an electronic device according to a method for determining data in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to an embodiment of the present application, an embodiment of a method for determining data is provided, and the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] In this embodiment, a method for determining data is proposed. The method can determine at least one associated chapter associated with the chapter to be processed in multiple historical chapters based on the first feature vector set of the chapter to be processed in the report. Furthermore, based on the behavior information of the target object, the chapter to be recommended in at least one associated chapter can be determined, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency.

[0029] Figure 1 FIG. 1 is a flow chart of a method for determining data according to an embodiment of the present application. Figure 1 As shown, the method may include the following steps:

[0030] Step S102, obtaining the to-be-processed chapters of the target object.

[0031] In the technical solution provided in the above step S102 of the present application, the above target object may be a staff member, a business person in a business unit or department, a document operator or editor, etc. The above chapter to be processed may be a chapter in a large report, or a chapter associated with a business unit or department. The above report may be a report to be processed, may include at least one chapter to be processed and / or at least one processed chapter, may be a large report to be compiled, or may be a report associated with a business unit or department. It should be noted that this is only an example, and there is no specific limitation on the type of report to be processed and the type of target object.

[0032] Optionally, the pending report input by the target object can be obtained through a terminal such as a computer or a mobile phone, and the pending chapters in the pending report can be determined through the user's selection instruction. Alternatively, the pending chapters can be directly obtained through user input. It should be noted that this is only an example, and the method for obtaining the pending chapters is not specifically limited.

[0033] Step S104: determining a first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or attribute information corresponding to the chapter to be processed.

[0034] In the technical solution provided in the above step S104 of the present application, the first feature vector set corresponding to the chapter to be processed can be determined. Among them, the above first feature vector set may include multiple sub-feature vectors, and the above first feature vector set can at least be used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed. The above text content can be used to characterize texts such as keywords and chapter names in the chapter, and can be used to determine information such as the table of contents and chapter content. The above attribute information may include the identification information (Identifier, referred to as ID) of the chapter, the title, category, department to which the chapter belongs, and other attributes. It should be noted that this is only an example, and there is no specific restriction on the type of text content and attribute information.

[0035] Optionally, feature extraction is performed on the chapters to be processed to obtain a first feature vector set corresponding to the chapters to be processed. For example, the chapters to be processed can be transformed by a feature extraction module to obtain a first feature vector set. It should be noted that this is only an example, and there is no specific limitation on the method for obtaining the first feature vector.

[0036] For example, through a feature extraction module, the table of contents and content of the chapter to be processed can be converted into a feature vector representation to obtain a first set of feature vectors. Among them, the above-mentioned feature extraction module can generate corresponding feature vector representations based on features such as the chapter to be processed and tag information obtained. The extraction of the first set of feature vectors can include the following steps: Use natural language processing tools (such as word segmentation tools, etc.) to segment the text of the preprocessed chapter to be processed into individual words. Count the frequency of each word in the chapter. Data structures such as hash tables can be used to quickly record words and their occurrence times. A stop word list (or a custom stop word list for a specific domain) can be loaded from an existing stop word library. The stop word list can contain some common words without practical meaning, such as "de", "shi", "zai", "le", etc. By using the stop word list, stop words in the text can be removed. Further, the term frequency-inverse document frequency (TF-IDF) model can be used to vectorize the text after removing stop words to obtain the first set of feature vectors corresponding to the chapter to be processed.

[0037] Optionally, by using the above TF-IDF model, the table of contents of the chapter and content keywords in the chapter, etc., can be extracted. The above TF-IDF model can construct a vector representation of the document by statistically calculating the frequency of occurrence of words (i.e., the above text) in the document and the inverse document frequency. It can be determined by the following formula:

[0038]

[0039] Among them, can be used to represent the feature vector of text conversion. IDF(t) can be used to represent the inverse document frequency. TF(t, d) can be used to represent the term frequency of each word, that is, the number of occurrences of the word in the chapter divided by the total number of words in the chapter

[0040] Optionally, for each chapter to be processed according to the above formula, count the number of occurrences of each word in the document (i.e., the chapter to be processed). Calculate the term frequency (TF) of each word, that is, the number of occurrences of the word in the chapter divided by the total number of words in the chapter. Count the number of chapters containing each word. Calculate the inverse document frequency (IDF), and the formula is IDF = log(total number of documents / number of documents containing the word). Multiply the term frequency (TF) and inverse document frequency (IDF) of each word to obtain the TF-IDF value of the word. Further, for all words in each chapter, sort them in descending order according to the TF-IDF value. Select several words with higher TF-IDF values as the keywords of the document.

[0041] Optionally, the specific number of keywords to be selected can be determined according to actual needs. Generally, the first 10-20 keywords for the content of the entire chapter can be selected. 1-2 keywords can be selected for the table of contents. 3-5 keywords can be selected for each chapter content. Through the above steps, the TF-IDF method can be used to extract keywords from the text. These keywords and their corresponding feature vectors can better reflect the theme and important content of the chapter. Among them, the first feature vector set may include feature vectors corresponding to the above keywords. It should be noted that the above method of obtaining the first feature vector set is only for example and is not specifically limited here.

[0042] Step S106, using the first feature vector set, determine at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or attribute information corresponding to the historical chapter.

[0043] In the technical solution provided in the above step S106 of the present application, the above historical chapters may be chapters stored in advance / input into a database, and may include historical business chapters, work summaries, etc. The above second feature vector set may be used to characterize the text content of the historical chapters and / or the attribute information corresponding to the historical chapters, and may include feature vectors corresponding to keywords in the historical chapters. It should be noted that this is only an example, and there is no specific limitation on the content of the second feature vector set.

[0044] Optionally, the historical feature vector set corresponding to the historical chapter is determined, and at least one second feature vector set associated with (or matched with) the first feature vector set is determined from the plurality of historical feature vectors in the first feature vector set, wherein the historical feature vector set includes at least one second feature vector set.

[0045] Step S108: determining at least one associated chapter associated with the chapter to be processed based on the second feature vector set.

[0046] In the technical solution provided in the above step S108 of the present application, the above-mentioned related chapters can be chapters that have been processed, read, or consulted by the target object in the historical report, and can be chapters similar to the chapter to be processed, for example, chapters with similar content and / or structure to the chapter to be processed. It should be noted that this is only an example, and there is no specific limitation on the type of chapter to be processed.

[0047] Optionally, historical chapters can be obtained in advance from multiple channels such as web pages and mobile terminals, and the historical chapters can be stored in the system. The TF-IDF model can be used to process the historical chapters stored in the system to obtain a historical feature vector set corresponding to each historical chapter. Further, based on the first feature vector set, at least one second feature vector set in the historical feature vector set can be determined, and based on the second feature vector set, an associated chapter with a high degree of association or high similarity with the chapter to be processed can be determined.

[0048] In this embodiment, the process of determining at least one associated chapter associated with the chapter to be processed based on the second feature vector set may include: determining the target chapter by determining the first matching degree between the second feature vector set and the first feature vector set, and determining the associated chapter based on the first association rule associated with the target chapter. Alternatively, the associated chapter may be determined by at least one frequent vector in the second feature vector set. The method for determining the associated chapter may be selected according to the actual situation, and is not specifically limited here.

[0049] Step S110 , determining a chapter to be recommended from at least one associated chapter based on the behavior information of the target object, wherein the behavior information is used to characterize the chapter preference of the target object.

[0050] In the technical solution provided in the above step S110 of the present application, the above behavior information can be used to characterize the chapter preference of the target object, which can be determined based on the reading history records of the historical chapters and the most recent historical chapters compiled by the user.

[0051] Optionally, the embodiment can identify user behavior to obtain behavior information, and based on the behavior information, it can determine the chapters that the user may be interested in, that is, it can determine the degree of preference of the target object for the associated chapters. Further, based on the behavior information, it can determine the chapters that the user is interested in (that is, the chapters to be recommended) from at least one associated chapter.

[0052] Through the above steps S102 and S110 of the present application, the chapter to be processed of the target object is obtained; the first feature vector set corresponding to the chapter to be processed is determined, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; using the first feature vector set, at least one second feature vector set associated with the chapter to be processed is determined in multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, at least one associated chapter associated with the chapter to be processed is determined; based on the behavior information of the target object, the chapter to be recommended is determined from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object. That is, in the embodiment of the present application, based on the first feature vector set of the chapter to be processed in the report, at least one associated chapter associated with the chapter to be processed is determined in multiple historical chapters, and further, based on the behavior information of the target object, the chapter to be recommended in at least one associated chapter is determined, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency.

[0053] The above method of this embodiment is further introduced below.

[0054] As an optional implementation, based on the second feature vector set, at least one associated chapter associated with the chapter to be processed is determined, including: determining a first matching degree between the second feature vector set and the first feature vector set; in response to the first matching degree being greater than a matching degree threshold, determining the historical chapter corresponding to the second feature vector set as the target chapter; obtaining a first association rule associated with the target chapter, wherein the first association rule is used to characterize the association relationship between multiple historical chapters; and determining at least one associated chapter from the database according to the first association rule.

[0055] In this embodiment, the second feature vector set and the first feature vector set can be matched to obtain a first matching degree between the second feature vector set and the first feature vector set, and based on the first matching degree, a target chapter in the historical chapter can be determined. A pre-constructed first association rule for associating the target chapter is obtained. Based on the first association rule, at least one associated chapter can be determined from the database.

[0056] Optionally, a first association rule corresponding to a historical chapter may be constructed in advance. Based on the second feature vector set and the first feature vector set, a target chapter in at least one historical chapter may be determined, and based on the first association rule of the target chapter, an associated chapter may be determined. The first association rule may be used to characterize the association relationship between multiple historical chapters. For example, the first association rule may be (Chapter 1, Chapter 2, Chapter 3, the three chapters are similar).

[0057] For example, the second feature vector set of the historical chapter is matched with the first feature vector set to obtain a first matching degree. In response to the first matching degree between the second feature vector set of historical chapter one and the first feature vector set being greater than a matching degree threshold, historical chapter one can be determined as the target chapter. A first association rule for historical chapter one can be obtained. For example, the first association rule can be: chapter one, chapter two, chapter three. If the above three chapters are similar, then chapter one, chapter two, and chapter three can be determined as associated chapters. Among them, the above matching degree threshold can be a pre-set value, and the method for determining the matching degree threshold is not specifically limited here.

[0058] Optionally, the embodiment can set a determination method of the first association rule, so that different first association rules between historical chapters can be pre-constructed, so that the purpose of quickly determining the associated chapters can be achieved based on the first association rule. It should be noted that the first association rule can be constructed based on the feature vectors, text keywords and other contents of the historical chapters, and the construction method of the first association rule is not specifically limited here.

[0059] For example, the similarities between multiple historical chapters can be determined in advance, and based on the similarities between the multiple historical chapters, the first association rule corresponding to the historical chapters can be determined. Alternatively, feature vectors corresponding to keywords in multiple historical chapters can be determined, and based on the feature vectors, the similarities between the multiple historical chapters can be determined to obtain the first association rule corresponding to the historical chapters.

[0060] As an optional implementation, based on the second feature vector set, determining at least one associated chapter associated with the chapter to be processed includes: determining at least one frequent vector from multiple second feature vector sets, wherein the frequent vector is used to represent a subvector in the second feature vector set whose number of appearances is greater than a number threshold; constructing a second association rule associated with the frequent vector, and respectively determining a second matching degree between at least one frequent vector and the first feature vector set, wherein the second association rule is used to represent the association relationship between the frequent vector and at least one historical chapter; in response to the second matching degree being greater than the matching degree threshold, determining at least one associated chapter from the historical chapters according to the second association rule associated with the frequent vector.

[0061] In this embodiment, a subvector whose number of occurrences in the second feature vector set is greater than the number threshold can also be determined, and the subvector can be determined as a frequent vector, thereby obtaining at least one frequent vector. Among them, the above-mentioned frequent vector can be a frequent item, which can be used to characterize the subvector whose number of occurrences in the second feature vector set is greater than the number threshold. Further, a second association rule associated with the frequent vector can be constructed. And the second matching degree of at least one frequent vector and the first feature vector set can be determined respectively, so that the target frequent vector whose second matching degree with the first feature vector set is greater than the matching degree threshold can be determined from multiple frequent vectors; based on the second association rule corresponding to the target frequent vector, at least one associated chapter can be determined. Among them, the above-mentioned second association rule can be used to characterize the association relationship between the frequent vector and at least one historical chapter. For example, the second association rule can be: the vectors corresponding to the bird and the chicken are associated with chapter one and chapter two. It should be noted that this is only an example, and there is no specific restriction on the method of determining the second association rule.

[0062] Optionally, the frequent vectors are matched with the first feature vector set respectively to obtain a second matching degree. If the second matching degree is greater than a matching degree threshold, at least one associated chapter may be determined based on a second association rule associated with the frequent vectors.

[0063] In this embodiment, the algorithm module for recommending corresponding content to the editor of the chapter based on the association rules of the chapter is the core of the entire association rule recommendation system. The module can calculate the recommendation result of the chapter similarity based on the structured feature vector of the chapter (that is, the vector included in the second feature vector set) using the corresponding recommendation algorithm. With the recommendation result, the editor can conveniently refer to the chapters that have been compiled before and have association rules with the chapter during the chapter compilation process.

[0064] Optionally, in order to find the relationship between project chapters in a large database, an association rule analysis method (such as Apriori algorithm) can be used. The following example illustrates the method of constructing the second association rule using the algorithm for mining frequent item sets, but it should be noted that this is only an example and does not specifically limit the method of constructing the second association rule.

[0065] For example, by searching layer by layer, a frequent item set is found from the candidate frequent item sets, and then a second association rule is generated according to the frequent item set. Optionally, constructing the second association rule may include the following contents:

[0066] A transaction can refer to each record in a data set. A transaction can contain several items. For example, in the association rule analysis of chapters, a transaction can be the attributes of a chapter and its corresponding feature vector, and the items in the transaction are the feature vectors in the second feature vector set.

[0067] An itemset is a set of one or more items. For example, if an itemset contains k items, it is called a k-itemset.

[0068] Support refers to the frequency with which an item set appears in all transactions. For example, the support of the item set {A, B} is the ratio of the number of transactions that contain both A and B to the total number of transactions. Support (X) can be used to reflect the prevalence of the item set and can be expressed as: Support (X) = count (X) / N, where count (X) can be used to represent the number of times the item set X appears, and N can be used to represent the total number of transactions.

[0069] Confidence can be used to measure the strength of association rules. For example, for rule X->Y, the confidence is equal to the ratio of the number of transactions containing X and Y (Support(X∪Y)) to the number of transactions containing X (Support(X)). The formula for the above confidence (Confidence(X->Y)) can be: Confidence(X->Y)=Support(X∪Y) / Support(X).

[0070] Frequent itemsets may refer to itemsets whose support is greater than or equal to a user-defined minimum support threshold.

[0071] Furthermore, relevant information of the historical chapters compiled by the user may be collected, which may include attributes such as ID, title, category, department, etc. of the historical chapters, and feature vectors such as keywords corresponding to the chapters. The second feature vector set may include the feature vectors mentioned above.

[0072] Optionally, the feature vectors are converted into a format suitable for Apriori algorithm processing, which may be in the form of a transaction database, wherein each row in the converted data represents a transaction (for example, attributes corresponding to a chapter, and feature vectors of keywords in a chapter, etc.), and each column represents a chapter item.

[0073] Optionally, a minimum support threshold and a minimum confidence threshold are determined. The minimum support (min_support) can be a pre-set threshold, which can be used to filter frequent item sets. The minimum confidence (min_confidence) can be a pre-set threshold, which can be used to filter strong association rules.

[0074] Optionally, scan the database, calculate the support of each individual item, filter out items greater than the minimum support, and form a 1-item frequent item set to complete the data initialization. Generate a k-item candidate item set based on the k-1 frequent item set, and then calculate the support of these candidate item sets. If any k-1 subset of a k-item candidate item set is not frequent, then the candidate item set cannot be frequent and can be pruned. Repeat the above steps until no more frequent item sets can be found. Further, for each frequent item set, all possible rules can be generated and the confidence of each rule can be calculated. For each frequent item set (L), the confidence of all its non-empty subsets can be calculated. Keep those rules whose confidence is greater than or equal to the minimum confidence threshold. All rules that meet the minimum support and minimum confidence threshold can be output, and these rules are regarded as strong association rules (that is, second association rules).

[0075] Optionally, a second association rule is constructed in the above manner. When a chapter to be processed is obtained, the frequent vectors (i.e., frequent items) in the second feature vector set can be determined, the target frequent vectors in the frequent vectors whose second matching degree with the first feature vector set is greater than the matching degree threshold are determined, and the second association rule corresponding to the target frequent vector is determined. Based on the second association rule, at least one associated chapter can be determined.

[0076] For example, suppose there is a transaction database containing the following:

[0077] Transaction 1: {Chapter 1, Chapter 2};

[0078] Transaction 3: {Chapter 2, Chapter 3};

[0079] After executing the Apriori algorithm, the following rules can be obtained:

[0080] If the user has read Chapter 1, then they are likely to have also read Chapter 2 (confidence: 0.8), and if the user has read Chapter 2, then they are likely to have also read Chapter 3 (confidence: 0.9). Therefore, if the user has recently read Chapter 1, we can recommend Chapter 2 based on the first rule.

[0081] Furthermore, the items in the transaction may include at least one frequent vector, and the first feature vector set may be matched with at least one frequent vector in the transaction to obtain a second matching degree. In response to the second matching degree being greater than a matching degree threshold, a target frequent vector that has been successfully matched may be determined. If the target frequent vector is a vector in transaction 1, the second association rule may be determined to be recommending chapter 1 and chapter 2 to the user.

[0082] Through the above steps, a recommendation system based on the Apriori algorithm can be built to help users find similar chapters that they may be interested in.

[0083] In this embodiment, historical chapters are recommended by analyzing chapter attributes of chapters, keywords in chapters, keywords in chapter directories, and other feature vectors. The core of this method is to find similarities between chapters and recommend similar chapters based on chapters and chapter directories.

[0084] In this embodiment, the user's response to the recommended chapters can also be monitored to collect the user's feedback information on the recommended chapters. Based on the feedback information, the recommendation effect can be evaluated to further analyze the performance of the recommendation system (or recommendation algorithm) and identify the improvement points that can be improved. Parameters such as the minimum support and the minimum confidence can be adjusted according to the evaluation results, and the Apriori algorithm can be re-run regularly to achieve the purpose of updating the frequent item sets (which can be transactions) and the second association rules.

[0085] When compiling large chapters in the traditional way, they are usually only allocated to business units and departments based on chapter attributes, and business personnel provide chapter information according to the chapter format guidance requirements. Most of the information involved (unstructured data) comes from historical business chapters, work summaries, and other contents. The information is highly repetitive and business personnel must repeat work, resulting in high labor costs for chapter compilation, slow iteration of knowledge coverage, and insufficient mining of employees' implicit knowledge. Therefore, in this embodiment, in order to solve the above problems, when compiling chapters, the association rules of the chapter relationship graph model are used to intelligently recommend the chapters. The matching degree of the catalog compiled by the chapters is relatively high, which can improve the quality and efficiency of the task, and the system can recommend the most suitable historical chapters according to different work requirements and task objectives, so as to achieve the purpose of improving the accuracy of the recommendation.

[0086] As an optional implementation, the method may also include: receiving multiple historical reports from multiple information collection channels, wherein the historical reports include at least one historical chapter; preprocessing the historical chapters; performing feature extraction on the preprocessed historical chapters to obtain a set of historical feature vectors corresponding to the preprocessed historical chapters.

[0087] In this embodiment, feature extraction is performed on the preprocessed historical chapters to obtain a second feature vector set corresponding to the preprocessed historical chapters, and it can also include: segmenting the text in the historical chapters to obtain multiple sub-texts; and constructing a historical feature vector set based on the frequency of occurrence of the sub-texts.

[0088] Optionally, the data access module is the first step in finding chapter associations. The above data access module can be used to collect historical chapters from multiple sources. The collected historical chapters may include structured and unstructured data, and the collected historical chapters may be integrated into a unified database. Different historical chapters are received and stored in the database through methods such as business personnel creating and importing, and Robotic Process Automation (RPA) uploading standardized chapters.

[0089] Optionally, the historical chapters are stored in a database, and the raw data (i.e., the initial historical chapters) collected from the data access module can be preprocessed, cleaned and normalized using a data preprocessing module. For example, punctuation marks, special characters, numbers and other elements in the historical chapters that may interfere with keyword extraction can be removed. The data preprocessing module can be classified according to content, and can filter out invalid data, remove outliers, process missing values, and standardize and normalize the historical chapter data into more useful feature information. Further, natural language processing tools (e.g., word segmentation tools, etc.) can be used to segment the text of the preprocessed historical chapters into independent words (i.e., subtexts). The frequency of occurrence of each word in the chapter is counted. Data structures such as hash tables can be used to quickly record words and their number of occurrences. Stop words are removed. Further, a vector representation of the document can be constructed by counting the frequency of occurrence of words in the document and the inverse document frequency to obtain a set of historical feature vectors corresponding to the historical chapters.

[0090] As an optional implementation, step S108, based on the behavior information of the target object, determines a chapter to be recommended from at least one associated chapter, including: based on the behavior information, determining the target object's preference for the associated chapter; in response to the preference degree being greater than a preference threshold, determining the associated chapter as a chapter to be recommended; in response to the preference degree being less than or equal to the preference threshold, determining the associated chapter as a non-chapter to be recommended.

[0091] In this embodiment, the preferences of the target object can also be taken into consideration, and the behavior information of the target object can be obtained. Based on the behavior information, the target object's preference degree for the associated chapter can be determined. Further, if the preference degree for the associated chapter is greater than the preference threshold, the associated chapter can be determined as a chapter to be recommended; in response to the preference degree being less than or equal to the preference threshold, the associated chapter can be determined as a non-chapter to be recommended.

[0092] Optionally, based on the behavior information, association rules containing chapter items that the user is interested in may be found to determine the chapters to be recommended.

[0093] In this embodiment, by establishing a relationship map of chapters, a complete set of relationship networks between chapters is constructed, and analysis and mining in the dimension of association relationships are increased to solve the "decentralization" pain points of traditional chapter compilation methods (i.e., high labor costs, slow coverage iteration, and weak AI intelligence). The background technology of the content-based chapter relationship map model analysis method relies on cutting-edge technologies such as artificial intelligence, big data processing, machine learning algorithms, and natural language processing. The comprehensive application of these technologies provides efficient and accurate information analysis tools for large-scale chapter compilation in enterprises. To support decision makers in making more scientific decisions, complex chapters of various types are displayed through data mining, information processing, knowledge measurement, and graphics drawing, revealing the dynamic development laws in the field of business knowledge, providing practical and valuable reference significance for business research, and providing zero cost for information exchange. The final result of the system implementation is efficiency, and the Pareto optimality of resource allocation is achieved, that is, improving efficiency means reducing waste.

[0094] In this embodiment, business data, system models and work tasks are fully combined to form a "three-in-one" report think tank architecture, reducing repeated information provision and improving employee productivity. The content-based chapter relationship graph model analysis method can help companies reduce the cost investment in information query and data reuse, especially in terms of manpower and time savings, and can also help users make better decisions.

[0095] Optionally, the chapter relationship graph model analysis method based on association rules is combined with cutting-edge technologies such as artificial intelligence and big data processing, and comprehensive application provides a business basis for supporting decision makers to make more scientific decisions. The application of intelligent algorithms in association rule recommendation has become more and more common and important. These algorithms can achieve comprehensive coverage of stock and incremental scenarios based on the historical and updated data of chapters, and recommend chapter content that meets the association relationship for the system's chapter compilation.

[0096] In an embodiment of the present application, based on the first feature vector set of the chapter to be processed in the report, at least one associated chapter associated with the chapter to be processed is determined among multiple historical chapters. Furthermore, based on the behavior information of the target object, a chapter to be recommended in at least one associated chapter can be determined, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency.

[0097] In this embodiment, in addition to recommending chapters similar to the chapter to be processed, chapters similar to the chapter to be processed can also be recommended to improve the user's processing efficiency of the chapter. It should be noted that there is no specific limitation on the object of recommendation, and any method for determining the text to be recommended through the above logic should be within the scope of protection of this application.

[0098] In the embodiment of the present application, another method for determining data is also provided. Figure 2 FIG. 1 is a flow chart of another method for determining data according to an embodiment of the present application. Figure 2 As shown, the method may include the following steps:

[0099] Step S202, obtaining the to-be-processed chapters of the target object.

[0100] Step S204: determining a first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or attribute information corresponding to the chapter to be processed.

[0101] Step S206, using the first feature vector set, determine at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or attribute information corresponding to the historical chapter.

[0102] Step S208: determining at least one associated chapter associated with the chapter to be processed based on the second feature vector set.

[0103] In the technical solution provided in the above step S208 of the present application, the first feature vector set can be used to match the historical feature vector set corresponding to the historical chapters to determine at least one second feature vector set associated with the chapter to be processed among multiple historical feature vector sets. Based on the second feature vector set, at least one associated chapter associated with the chapter to be processed can be determined.

[0104] Step S210, determining the relevance between at least one related chapter and the chapter to be processed.

[0105] In the technical solution provided in the above step S210 of the present application, after determining the associated report, in order to improve the accuracy of the report to be recommended, the degree of association between the associated report and the report to be processed may be determined.

[0106] Step S212: determining a chapter to be recommended from at least one related chapter based on the degree of relevance.

[0107] In the technical solution provided in the above step S212 of the present application, based on the degree of association, the chapter to be recommended in at least one associated report can be determined.

[0108] For example, at least one associated chapter associated with the chapter to be processed is determined, and the degree of association between the associated chapter and the chapter to be processed is determined. Based on the degree of association, a chapter to be recommended whose degree of association is greater than a threshold value of the degree of association in at least one associated chapter can be determined, and at least one chapter to be recommended can be obtained. Based on the at least one chapter to be recommended, a recommendation list can be created, and the recommendation list can include at least one chapter to be recommended. The recommendation list can be displayed on the user interface in the form of a list, card, or pop-up window. The reason for the recommendation is explained to the target object, for example, "Since you have read Chapter 1 or compiled Chapter 1 before, and Chapter 1 has a high degree of association with the chapter to be recommended, we recommend that you read Chapter 3."

[0109] In an embodiment of the present application, a chapter to be processed of a target object is obtained; a first feature vector set corresponding to the chapter to be processed is determined, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; using the first feature vector set, at least one second feature vector set associated with the chapter to be processed is determined from multiple historical feature vector sets, wherein the second feature vector set is used to characterize at least the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, at least one associated chapter associated with the chapter to be processed is determined; the degree of association between at least one associated chapter and the chapter to be processed is respectively determined; based on the degree of association, a chapter to be recommended is determined in at least one associated chapter, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency.

[0110] According to an embodiment of the present application, a data determination device is also provided. It should be noted that the data determination device of this embodiment can be used to execute the data determination method of the above embodiment of the present application.

[0111] Figure 3 is a schematic diagram of a data determination device according to an embodiment of the present application. Figure 3 As shown, the data determination device 30 may include: a first acquisition unit 302 , a first determination unit 304 , a second determination unit 306 , a third determination unit 308 and a fourth determination unit 310 .

[0112] The first acquisition unit 302 is used to acquire the to-be-processed chapters of the target object.

[0113] The first determining unit 304 is used to determine a first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed.

[0114] The second determination unit 306 is used to determine at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets using the first feature vector set, wherein the second feature vector set is used to at least represent the text content of the historical chapter and / or attribute information corresponding to the historical chapter.

[0115] The third determining unit 308 is configured to determine at least one associated chapter associated with the to-be-processed chapter based on the second feature vector set.

[0116] The fourth determining unit 310 is configured to determine a chapter to be recommended from at least one associated chapter based on behavior information of the target object, wherein the behavior information is used to characterize the chapter preference of the target object.

[0117] The data determination device of this embodiment obtains the to-be-processed chapter of the target object through a first acquisition unit; determines a first feature vector set corresponding to the to-be-processed chapter through a first determination unit, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or the attribute information corresponding to the to-be-processed chapter; determines at least one second feature vector set associated with the to-be-processed chapter from multiple historical feature vector sets using the first feature vector set through a second determination unit, wherein the second feature vector set is used to characterize at least the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; determines at least one associated chapter associated with the to-be-processed chapter based on the second feature vector set through a third determination unit; determines a to-be-recommended chapter from at least one associated chapter based on the behavior information of the target object through a fourth determination unit, wherein the behavior information is used to characterize the chapter preference of the target object, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency.

[0118] According to an embodiment of the present application, another data determination device is also provided. It should be noted that the data determination device of this embodiment can be used to execute the data determination method of the above embodiment of the present application.

[0119] Figure 4 FIG. 1 is a schematic diagram of another data determination device according to an embodiment of the present application. Figure 4 As shown, the data determination device 40 may include: a second acquisition unit 402 , a fifth determination unit 404 , a sixth determination unit 406 , a seventh determination unit 408 , an eighth determination unit 410 and a ninth determination unit 412 .

[0120] The second acquisition unit 402 is used to acquire the to-be-processed chapters of the target object.

[0121] The fifth determining unit 404 is used to determine a first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or attribute information corresponding to the chapter to be processed.

[0122] The sixth determination unit 406 is used to determine at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets using the first feature vector set, wherein the second feature vector set is used to at least represent the text content of the historical chapter and / or attribute information corresponding to the historical chapter.

[0123] The seventh determining unit 408 is configured to determine at least one associated chapter associated with the to-be-processed chapter based on the second feature vector set.

[0124] The eighth determining unit 410 is used to determine the relevance between at least one associated chapter and the chapter to be processed.

[0125] The ninth determining unit 412 is configured to determine a chapter to be recommended from at least one related chapter based on the degree of association.

[0126] The data determination device of this embodiment obtains the report to be processed of the target object through the second acquisition unit. The fifth determination unit 404 determines the chapter to be processed in the report to be processed. The third feature vector set corresponding to the chapter to be processed is determined by the sixth determination unit, wherein the third feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed. The seventh determination unit uses the third feature vector set to determine at least one associated chapter associated with the chapter to be processed in multiple historical chapters. The eighth determination unit determines the degree of association between at least one associated chapter and the chapter to be processed. The ninth determination unit determines the chapter to be recommended in at least one associated chapter based on the degree of association, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency.

[0127] The embodiment of the present application may provide a computer terminal, which may be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced by a terminal device such as a mobile terminal.

[0128] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0129] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the data determination method: obtaining the chapter to be processed of the target object; determining the first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; using the first feature vector set, determining at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determining at least one associated chapter associated with the chapter to be processed; based on the behavior information of the target object, determining the chapter to be recommended from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object.

[0130] Optionally, Figure 5 is a structural block diagram of a computer terminal according to an embodiment of the present application, such as Figure 5 As shown, the computer terminal 508 may include: one or more (only one is shown in the figure) processors 502 , a memory 504 , and a transmission device 506 .

[0131] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the data determination method and device in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned data determination method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 508 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0132] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the chapter to be processed of the target object; determine the first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; use the first feature vector set to determine at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determine at least one associated chapter associated with the chapter to be processed; based on the behavior information of the target object, determine the chapter to be recommended from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object.

[0133] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the computer terminal 508 may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID for short), a PAD, or other terminal devices. Figure 5 The structure of the computer terminal 508 is not limited. For example, the computer terminal 508 may also include Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 5 Different configurations shown.

[0134] A person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0135] According to an embodiment of the present application, a computer-readable storage medium is further provided, the computer-readable storage medium including a stored program, wherein the program executes the method for determining data in the above embodiment.

[0136] Optionally, in this embodiment, the computer-readable storage medium may be located in any one of the computer terminals in a computer terminal group in a computer network, or in any one of the mobile terminals in a mobile terminal group.

[0137] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining a chapter to be processed of a target object; determining a first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; using the first feature vector set, determining at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determining at least one associated chapter associated with the chapter to be processed; based on the behavior information of the target object, determining a chapter to be recommended from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object.

[0138] Optionally, the computer-readable storage medium may also execute program code for the following steps: determining a first degree of match between the second feature vector set and the first feature vector set; in response to the first degree of match being greater than a matching degree threshold, determining the historical chapter corresponding to the second feature vector set as a target chapter; obtaining a first association rule associated with the target chapter, wherein the first association rule is used to characterize an association relationship between multiple historical chapters; and determining at least one associated chapter from a database according to the first association rule.

[0139] Optionally, the computer-readable storage medium may also execute program code for the following steps: determining at least one frequent vector from a plurality of second feature vector sets, wherein the frequent vector is used to characterize a subvector in the second feature vector set that appears more than a threshold number of times; constructing a second association rule associated with the frequent vector, and determining a second degree of match between at least one frequent vector and the first feature vector set, respectively, wherein the second association rule is used to characterize the association relationship between the frequent vector and at least one historical chapter; in response to the second degree of match being greater than the threshold number of matches, determining at least one associated chapter from the historical chapters according to the second association rule associated with the frequent vector.

[0140] Optionally, the computer-readable storage medium may also execute program code for the following steps: receiving multiple historical reports from multiple information collection channels, wherein the historical reports include at least one historical chapter; preprocessing the historical chapters; performing feature extraction on the preprocessed historical chapters to obtain a set of historical feature vectors corresponding to the preprocessed historical chapters.

[0141] Optionally, the computer-readable storage medium may also execute program code for the following steps: segmenting the text in the historical chapter to obtain a plurality of sub-texts; and constructing a historical feature vector set based on the occurrence frequency of the sub-texts.

[0142] Optionally, the computer-readable storage medium may also execute program code for the following steps: based on the behavior information, determining the target object's preference for the associated chapter; in response to the preference degree being greater than a preference threshold, determining the associated chapter as a chapter to be recommended; in response to the preference degree being less than or equal to the preference threshold, determining the associated chapter as a non-chapter to be recommended.

[0143] Optionally, in this embodiment, the computer-readable storage medium is configured to store program codes for executing the following steps: obtaining a chapter to be processed of a target object; determining a first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; using the first feature vector set, determining at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determining at least one associated chapter associated with the chapter to be processed; respectively determining the degree of association between at least one associated chapter and the chapter to be processed; based on the degree of association, determining a chapter to be recommended in at least one associated chapter.

[0144] In this embodiment, based on the first feature vector set of the chapter to be processed in the report, at least one associated chapter associated with the chapter to be processed is determined among multiple historical chapters. Furthermore, based on the behavior information of the target object, a chapter to be recommended in at least one associated chapter can be determined, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency.

[0145] According to an embodiment of the present application, a processor is further provided, which is used to run a program, wherein the method for determining data in the above embodiment is executed when the program is run by the processor.

[0146] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0147] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the data determination method: obtaining the chapter to be processed of the target object; determining the first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; using the first feature vector set, determining at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determining at least one associated chapter associated with the chapter to be processed; based on the behavior information of the target object, determining the chapter to be recommended from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object.

[0148] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for determining data in the embodiment of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method for determining data. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0149] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the chapter to be processed of the target object; determine the first feature vector set corresponding to the chapter to be processed, wherein the first feature vector set is at least used to characterize the text content of the chapter to be processed and / or the attribute information corresponding to the chapter to be processed; use the first feature vector set to determine at least one second feature vector set associated with the chapter to be processed from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determine at least one associated chapter associated with the chapter to be processed; based on the behavior information of the target object, determine the chapter to be recommended from at least one associated chapter, wherein the behavior information is used to characterize the chapter preference of the target object.

[0150] Optionally, the processor may also execute program code for the following steps: determining a first degree of match between the second feature vector set and the first feature vector set; in response to the first degree of match being greater than a matching degree threshold, determining the historical chapter corresponding to the second feature vector set as a target chapter; obtaining a first association rule associated with the target chapter, wherein the first association rule is used to characterize an association relationship between multiple historical chapters; and determining at least one associated chapter from a database according to the first association rule.

[0151] Optionally, the processor may also execute program code for the following steps: determining at least one frequent vector from a plurality of second feature vector sets, wherein the frequent vector is used to represent a subvector in the second feature vector set that appears more than a threshold number of times; constructing a second association rule associated with the frequent vector, and determining a second degree of match between at least one frequent vector and the first feature vector set, respectively, wherein the second association rule is used to represent the association relationship between the frequent vector and at least one historical chapter; in response to the second degree of match being greater than the threshold number of matches, determining at least one associated chapter from the historical chapters according to the second association rule associated with the frequent vector.

[0152] Optionally, the processor may also execute program code for the following steps: receiving multiple historical reports from multiple information collection channels, wherein the historical reports include at least one historical chapter; preprocessing the historical chapters; performing feature extraction on the preprocessed historical chapters to obtain a set of historical feature vectors corresponding to the preprocessed historical chapters.

[0153] Optionally, the processor may also execute program codes of the following steps: segmenting the text in the historical chapters to obtain a plurality of sub-texts; and constructing a historical feature vector set based on the occurrence frequencies of the sub-texts.

[0154] Optionally, the processor may also execute program code for the following steps: based on the behavior information, determining the target object's preference for the associated chapter; in response to the preference degree being greater than a preference threshold, determining the associated chapter as a chapter to be recommended; in response to the preference degree being less than or equal to the preference threshold, determining the associated chapter as a non-chapter to be recommended.

[0155] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the data determination method: obtaining the to-be-processed chapter of the target object; determining the first feature vector set corresponding to the to-be-processed chapter, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or the attribute information corresponding to the to-be-processed chapter; using the first feature vector set, determining at least one second feature vector set associated with the to-be-processed chapter from multiple historical feature vector sets, wherein the second feature vector set is used to at least characterize the text content of the historical chapter and / or the attribute information corresponding to the historical chapter; based on the second feature vector set, determining at least one associated chapter associated with the to-be-processed chapter; respectively determining the degree of association between at least one associated chapter and the to-be-processed chapter; based on the degree of association, determining the chapter to be recommended from at least one associated chapter.

[0156] By adopting the embodiment of the present application, based on the first feature vector set of the chapter to be processed in the report, at least one related chapter associated with the chapter to be processed is determined among multiple historical chapters. Furthermore, based on the behavior information of the target object, a chapter to be recommended in at least one related chapter can be determined, thereby solving the technical problem of low data processing efficiency and achieving the technical effect of improving data processing efficiency.

[0157] According to an embodiment of the present application, a computer program product is also provided. The computer program product includes computer instructions, wherein when the computer instructions are executed by a processor, the method for determining data in the above embodiment is implemented.

[0158] An embodiment of the present application may provide an electronic device, which may include a memory and a processor.

[0159] Figure 6It is a block diagram of an electronic device according to a method for determining data in an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0160] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 to a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0161] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0162] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a data verification method. For example, in some embodiments, the data verification method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the data verification method described above may be executed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute the data verification method in any other appropriate manner (for example, by means of firmware).

[0163] According to an embodiment of the present application, a method for determining data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0164] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0165] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0166] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0167] To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or an LCD (liquid crystal display, monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or a path ball) through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0168] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a Local Area Network (LAN), a Wide Area Network (WAN), and the Internet.

[0169] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0170] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0171] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0172] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0173] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0174] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0175] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0176] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining data, characterized in that: include: Get the pending chapters of the target object; Determine a first feature vector set corresponding to the to-be-processed chapter, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or attribute information corresponding to the to-be-processed chapter; Determine, using the first feature vector set, at least one second feature vector set associated with the chapter to be processed from a plurality of historical feature vector sets, wherein the second feature vector set is used to at least represent the text content of the historical chapter and / or attribute information corresponding to the historical chapter; Based on the second feature vector set, determining at least one associated chapter associated with the to-be-processed chapter; Determining a chapter to be recommended from the at least one associated chapter based on the behavior information of the target object, wherein the behavior information is used to characterize the chapter preference of the target object; Among them, the method of determining at least one associated chapter associated with the to-be-processed chapter based on the second feature vector set includes: determining at least one frequent vector from multiple second feature vector sets, wherein the frequent vector is used to represent a subvector in the second feature vector set whose number of appearances is greater than a number threshold; respectively determining a second matching degree between at least one of the frequent vectors and the first feature vector set corresponding to the to-be-processed chapter; determining the frequent vector whose second matching degree is greater than the matching degree threshold as a target frequent vector; determining a second association rule associated with the target frequent vector; and determining at least one associated chapter from the historical chapters based on the second association rule, wherein the second association rule is used to represent the association relationship between the frequent vector and the historical chapter.

2. The method according to claim 1, characterized in that The determining, based on the second feature vector set, at least one associated chapter associated with the to-be-processed chapter further includes: determining a first degree of matching between the second feature vector set and the first feature vector set; In response to the first matching degree being greater than a matching degree threshold, determining the historical chapter corresponding to the second feature vector set as a target chapter; Acquire a first association rule associated with the target chapter, wherein the first association rule is used to characterize an association relationship between the multiple historical chapters; According to the first association rule, at least one associated chapter is determined from a database.

3. The method according to claim 1, characterized in that The method further comprises: The second association rule associated with the frequent vector is constructed.

4. The method according to claim 1, characterized in that: The method further comprises: Receiving a plurality of history reports from a plurality of information collection channels, wherein the history reports include at least one history section; Preprocessing the historical chapters; Feature extraction is performed on the preprocessed historical chapters to obtain the historical feature vector set corresponding to the preprocessed historical chapters.

5. The method according to claim 4, characterized in that The step of extracting features from the preprocessed historical chapters to obtain the historical feature vector set corresponding to the preprocessed historical chapters includes: Segmenting the text in the history chapter to obtain multiple sub-texts; The historical feature vector set is constructed based on the occurrence frequency of the subtext.

6. The method according to claim 1, characterized in that The step of determining a chapter to be recommended from the at least one associated chapter based on the behavior information of the target object includes: Based on the behavior information, determining the target object's preference for the associated chapter; In response to the preference degree being greater than a preference threshold, determining the associated chapter as the chapter to be recommended; In response to the preference degree being less than or equal to a preference threshold, it is determined that the associated chapter is not the to-be-recommended chapter.

7. A method for determining data, characterized in that: include: Get the pending chapters of the target object; Determine a first feature vector set corresponding to the to-be-processed chapter, wherein the first feature vector set is at least used to characterize the text content of the to-be-processed chapter and / or attribute information corresponding to the to-be-processed chapter; Determine, using the first feature vector set, at least one second feature vector set associated with the chapter to be processed from a plurality of historical feature vector sets, wherein the second feature vector set is used to at least represent the text content of the historical chapter and / or attribute information corresponding to the historical chapter; Based on the second feature vector set, determining at least one associated chapter associated with the to-be-processed chapter; Respectively determining the relevance between at least one of the associated chapters and the chapter to be processed; Based on the relevance, determining a chapter to be recommended in at least one of the related chapters; Among them, the method of determining at least one associated chapter associated with the to-be-processed chapter based on the second feature vector set includes: determining at least one frequent vector from multiple second feature vector sets, wherein the frequent vector is used to represent a subvector in the second feature vector set whose number of appearances is greater than a number threshold; respectively determining a second matching degree between at least one of the frequent vectors and the first feature vector set corresponding to the to-be-processed chapter; determining the frequent vector whose second matching degree is greater than the matching degree threshold as a target frequent vector; determining a second association rule associated with the target frequent vector; and determining at least one associated chapter from the historical chapters based on the second association rule, wherein the second association rule is used to represent the association relationship between the frequent vector and the historical chapter.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

9. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the method according to any one of claims 1 to 7.

10. A processor, characterized in that: The processor is used to run a program, wherein the program executes the method according to any one of claims 1 to 7 when run by the processor.

Images