Input method association method, input method association device and computer storage medium

Abstract

The invention provides an input method association method, an input method association device and a computer storage medium. The method comprises the steps of obtaining a first expected bucket and a second expected bucket, wherein the first expected bucket and the second expected bucket are constructed from different data dimensions; obtaining a first expected word combination of the to-be-associated word in the first expected bucket and a first expected score of each expected word; obtaining a second expected word combination of the to-be-associated word in a second expected bucket and a second expected score of each expected word; the first expected word combination and the second expected word combination are combined, a third expected word combination is generated, and third expected scores of expected words in the third expected word combination are subjected to weighted fusion through the first expected score in the first expected bucket and the second expected score in the second expected bucket; and performing input method association output on the third expected word combination according to the third expected score. Through the input method association method, the accuracy of input method association is realized by using multiple expectations of different data dimensions, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of input methods, and in particular to an input method association method, an input method association device and a computer storage medium. Background Art

[0002] The input method association function is to input a Chinese character, and the input method automatically recommends candidate characters and words. This method simplifies the number of keystrokes when the user inputs, and speeds up the input speed. When the user inputs a character, the input method will automatically return the most common phrases that match this character.

[0003] Since association is a possible next sentence that may appear from the previous sentence, this next sentence will be particularly divergent. Evaluating the effectiveness of an effect from just one expectation will result in deviations in many scenarios. However, when evaluating multiple expectations, it is impossible to judge the importance of each expectation. Summary of the invention

[0004] In order to solve the above technical problems, the present application proposes an input method association method, an input method association device and a computer storage medium.

[0005] In order to solve the above technical problems, the present application proposes an input method association method, which includes:

[0006] Obtaining a first expected bucket and a second expected bucket, wherein the first expected bucket and the second expected bucket are constructed from different data dimensions respectively;

[0007] Input the word to be associated;

[0008] Obtaining a first expected word combination of the to-be-associated word in the first expected bucket and a first expected score of each expected word thereof;

[0009] Obtain a second expected word combination of the to-be-associated word in the second expected bucket and a second expected score of each expected word thereof;

[0010] The first expected word combination and the second expected word combination are combined to generate a third expected word combination, wherein a third expected score of the expected word in the third expected word combination is weightedly fused by the first expected score of the first expected bucket and the second expected score of the second expected bucket;

[0011] The third expected word combination is output through input method association according to the third expected score.

[0012] Wherein, the first expected bucket is the data source expected bucket;

[0013] The input method association method further includes:

[0014] Get the data source association collection;

[0015] Based on the data source association set, a plurality of data source association input words and data source association expected combinations are segmented;

[0016] Based on the number of occurrences of a combination of the same data source associative input words, obtaining data source association scores expected for all data source associations associated with the data source associative input words;

[0017] The data source expected word of the data source associated input word is screened out based on the data source association scores expected by all data source associations, and the data source expected score of the data source expected word is obtained.

[0018] The step of selecting the data source expected word of the data source associated input word based on the data source association scores expected by all data source associations, and obtaining the data source expected score of the data source expected word includes:

[0019] Sort all data source association expectations from high to low based on their data source association scores;

[0020] Acquire a preset number of data source associative input words sorted from high to low as the data source expected words;

[0021] Get the total score of data source association scores of all data source association input words;

[0022] The data source expected score of each data source expected word is determined based on the ratio of the data source association score of each data source expected word to the total score.

[0023] Wherein, the second expected bucket is a version expected bucket;

[0024] The input method association method further includes:

[0025] Get the version association combination of each input method version;

[0026] Segmenting a plurality of combinations of version association input words and version association expectations based on the version association combination;

[0027] Based on the expected number of versions associated with each version association input word and the expected positions of the associated versions, obtain the expected version association scores of all the associated versions;

[0028] Based on the version association scores of all version association expectations, the version expected words of the version association input words are screened out, and the version expected scores of the version expected words are obtained.

[0029] The step of obtaining the expected version association scores of all associated version associations based on the number of associated version associations and the position of the associated version associations of each version association input word includes:

[0030] Based on the expected version position of each version association and the number of compared versions, obtain the version position score of each version position;

[0031] According to all version position scores and the number of appearing versions, the version association score expected for each version association is obtained.

[0032] The first expected bucket and the second expected bucket are expected buckets formed for all user data.

[0033] Wherein, after merging the first expected word combination and the second expected word combination to generate a third expected word combination, the input method association method further includes:

[0034] Obtain historical association data of the user who inputs the word to be associated;

[0035] Acquire a historical association score of the third expected word combination from the historical association data;

[0036] The third expected score is updated based on the historical association score.

[0037] The first expected bucket and the second expected bucket are expected buckets constructed for separate user data.

[0038] To solve the above technical problems, the present application also proposes an input method association device, which includes a memory and a processor coupled to the memory; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the input method association method as described above.

[0039] In order to solve the above technical problems, the present application also proposes a computer storage medium, which is used to store program data. When the program data is executed by a computer, it is used to implement the above input method association method.

[0040] Compared with the prior art, the beneficial effects of the present application are as follows: the input method association device obtains a first expected bucket and a second expected bucket, wherein the first expected bucket and the second expected bucket are constructed from different data dimensions respectively; inputs a word to be associated; obtains a first expected word combination of the word to be associated in the first expected bucket and a first expected score of each expected word; obtains a second expected word combination of the word to be associated in the second expected bucket and a second expected score of each expected word; merges the first expected word combination with the second expected word combination to generate a third expected word combination, wherein the third expected score of the expected word in the third expected word combination is weightedly fused by the first expected score in the first expected bucket and the second expected score in the second expected bucket; outputs the third expected word combination by input method association according to the third expected score. Through the above-mentioned input method association method, multiple expectations of different data dimensions are used to achieve the accuracy of input method association, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] in:

[0043] Figure 1 It is a flowchart of an embodiment of an input method association method provided by the present application;

[0044] Figure 2 It is a flowchart of an embodiment of a method for constructing an expected bucket of a data source provided by the present application;

[0045] Figure 3 This is a data schematic diagram of an embodiment of an expected bucket of a data source provided by the present application;

[0046] Figure 4 It is a flowchart of an embodiment of a method for constructing an expected version bucket provided by the present application;

[0047] Figure 5 This is a data schematic diagram of an embodiment of the version expected bucket 1 provided by this application;

[0048] Figure 6 This is a data schematic diagram of an embodiment of merging expected buckets provided by the present application;

[0049] Figure 7 This is a data schematic diagram of an embodiment of merging expected bucket test results provided by the present application;

[0050] Figure 8It is a flowchart of another embodiment of the input method association method provided by the present application;

[0051] Fig. 9 It is a structural diagram of an embodiment of an input method association device provided by the present application;

[0052] Fig.10 It is a structural diagram of an embodiment of a computer storage medium provided by the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions 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 are within the scope of protection of this application.

[0054] The terms "first", "second", "third", "fourth", etc. (if any) 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, for example, 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 that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] In order to solve the problem of input method association in the prior art, this application provides an input method association method based on multiple expectations. For details, please refer to Figure 1 , Figure 1 It is a flowchart of an embodiment of the input method association method provided by the present application.

[0056] The input method association method of the present application is applied to an input method association device, wherein the input method association device of the present application can be a server, can be a terminal device, or can be a system in which the server and the terminal device cooperate with each other. Accordingly, the various parts included in the input method association device, such as various units, subunits, modules, and submodules, can all be arranged in the server, can all be arranged in the terminal device, or can be arranged in the server and the terminal device respectively.

[0057] Furthermore, the above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here.

[0058] like Figure 1 As shown, the specific steps are as follows:

[0059] Step S11: Obtain a first expected bucket and a second expected bucket, wherein the first expected bucket and the second expected bucket are constructed from different data dimensions respectively.

[0060] In an embodiment of the present application, the input method association device obtains a pre-constructed first expected bucket and a second expected bucket. Among them, the expected bucket of the present application stores a combination of several input words and associated words, that is, a data set of association pairs. The expected bucket constructed by the present application can be constructed according to different data dimensions. For example, the input method association device constructs a data source expected bucket based on the full data source, that is, obtains all the input method data of the user; the input method association device constructs a version expected bucket based on the user input method data of each input method version; the input method association device constructs a time expected bucket based on the user input method data of different usage time periods, etc., wherein the usage time period can be each cycle, such as the input method data in January and the input method data in February, or it can be a fixed time period in each cycle, such as the input method data during working hours in a day and the input method data during rest time in a day.

[0061] By constructing expected buckets of different data dimensions, the present application can integrate expected information of multiple data dimensions when implementing input method association, thereby improving the input method association effect, enhancing the user experience, and making the association effect more in line with user needs.

[0062] The following describes the construction process of expected buckets for different data dimensions of this application using data source expected buckets and version expected buckets respectively:

[0063] Please refer to Figure 2 , Figure 2 It is a flowchart of an embodiment of a method for constructing expected buckets of a data source provided in this application.

[0064] like Figure 2 As shown, the specific steps are as follows:

[0065] Step S21: Obtain a data source association set.

[0066] In the embodiment of the present application, the input method association device obtains the user's input method data source, that is, a large amount of input method history records about the user. Among them, the user in the embodiment of the present application can refer to all users, in which case a universal expected bucket is constructed; it can also refer to a specific target user, in which case a personalized expected bucket is constructed. The construction process of the two is basically the same, and will not be repeated one by one later.

[0067] Step S22: dividing a plurality of data source association input words and data source association expected combinations based on the data source association set.

[0068] In the embodiment of the present application, the input method association device uses a segmentation model to segment the user's input method history records into one or more combinations of associative input words and associative expectations, that is, to construct associative pairs. The segmented associative input words and associative expectations have a contextual relationship in the input method history records.

[0069] Step S23: based on the number of occurrences of the combination of the same data source associative input word, obtaining the data source association scores of all data source association expectations associated with the data source associative input word.

[0070] In the embodiment of the present application, the input method association device counts the number of occurrences of each association pair in the entire data source, and uses the number of occurrences as the association score N of the association pair. Since the correlation required by the input method association is relatively high, the input method association device can take the top 20 association pairs with the highest association scores and retain them in the data source expected bucket. In other embodiments, the top 10 association pairs can also be taken, and the number can be specified by the staff.

[0071] Step S24: Filter out the data source expected words of the data source association input words based on the data source association scores expected by all data source associations, and obtain the data source expected scores of the data source expected words.

[0072] In the embodiment of the present application, the input method association device screens out a number of expected data source words in step S23, and determines the association score N of each expected data source word. Then, the input method association device counts the total score sumN of all the association pairs divided in step S22, and the calculation method is to add the association scores N of all the association pairs, and the final calculated sum is the total score sumN.

[0073] Thus, the input method association device calculates the expected score of each data source expected word according to the total score sumN of all association pairs and the association score of each data source expected word:

[0074] S=N / sumN

[0075] Please refer to Figure 3 , Figure 3It is a data schematic diagram of an embodiment of the data source expected bucket provided by this application. As Figure 3 shown, the input method association device obtains multiple expected words of the input word "not believe", as well as their association scores and expected scores according to the Figure 2 construction method shown. All this part of the data is stored in the data source expected bucket, which is convenient for subsequent expected bucket merging and score calculation.

[0076] Specifically, please refer to Figure 4 , Figure 4 which is a schematic flowchart of an embodiment of the version expected bucket construction method provided by this application.

[0077] As Figure 4 shown, the specific steps are as follows:

[0078] Step S31: Obtain the version association combinations of each input method version.

[0079] In the embodiments of this application, the input method association device obtains a large number of input method historical records generated by the user when using the input method in different input method versions. Among them, the user in the embodiments of this application can refer to all users, and at this time, a general expected bucket is constructed; it can also refer to a certain specific target user, and at this time, a personalized expected bucket is constructed. The construction processes of the two are basically the same, and will not be repeated one by one later.

[0080] Step S32: Based on the version association combinations, split out several version association input words and version association expected combinations.

[0081] In the embodiments of this application, the input method association device uses a segmentation model to segment the user's input method historical records into one or more association input words and association expected combinations, that is, constructs association pairs. Among them, the association input words and association expectations obtained by segmentation have a context relationship in the input method historical records.

[0082] Step S33: Based on the number of versions in which the version association expectations associated with each version association input word appear, and the version positions where they appear, obtain the version association scores of all the associated version association expectations.

[0083] In the embodiments of this application, the input method association device counts the number of versions n in which each association pair appears in the entire data source. For example, if an association pair appears in versions 1, 3, and 4, the number of versions in which this association pair appears is 3. In addition, the input method association device also needs to record the version positions where the association pair appears each time, that is, versions 1, 3, and 4 in the above example.

[0084] The input method association device obtains the total number of versions v_num of this input method, and calculates the association score of each association pair based on this:

[0085] N = n + [(6 - i1) * (1 / (v_num * 5)) + (6 - i2) * (1 / (v_num * 5)) +...]

[0086] Among them, i1, i2,... are different versions of the input method, that is, the occurrence version positions of the Lenovo pairs; 6 is the latest version, and in other embodiments, it can also be other values.

[0087] It should be noted that the above formula for calculating the Lenovo score refers to both the number of occurrence versions and the occurrence version positions of the Lenovo pairs, which can reflect the actual usage of the Lenovo pairs and is beneficial to determining accurate version expected words. In addition, the above formula for calculating the Lenovo score can also make the influence brought by the expected occurrence position less than the influence brought by the expected occurrence quantity.

[0088] Step S34: Screen out the version expected words of the version Lenovo input words based on the version Lenovo scores expected by all versions, and obtain the version expected scores of the version expected words.

[0089] In the embodiments of the present application, due to the relatively high relevance required by the input method Lenovo, the input method Lenovo device can retain the top 20 Lenovo pairs with the highest Lenovo scores into the version expected bucket. In other embodiments, the top 10 Lenovo pairs can also be taken, and the quantity can be specified by the staff.

[0090] The input method Lenovo device screens out several version expected words and determines the Lenovo score N of each version expected word. Then, the input method Lenovo device calculates the total score sumN of all the Lenovo pairs segmented in step S32, and its calculation method is to add up the Lenovo scores N of all the Lenovo pairs, and the final calculated sum is the total score sumN.

[0091] Thus, the input method Lenovo device calculates the expected scores of each version expected word according to the total score sumN of all the Lenovo pairs and the Lenovo scores of each version expected word:

[0092] S = N / sumN

[0093] For details, please refer to Figure 5 , Figure 5 is a data schematic diagram of an embodiment of the version expected bucket provided by the present application. As Figure 5 shown, the input method Lenovo device obtains multiple expected words of the input word "not believe", their Lenovo scores and expected scores according to the construction method shown in Figure 4 . All this part of the data is stored in the version expected bucket, which is convenient for subsequent merging of the expected buckets and score calculation.

[0094] Step S12: Input the word to be associated.

[0095] In the embodiment of the present application, the input method association device obtains the to-be-associated word input by the user using the current input method.

[0096] Step S13: Obtain the first expected word combination of the to-be-associated word in the first expected bucket and the first expected score of each expected word.

[0097] In the embodiment of the present application, the input method association device is in the first expected bucket, such as Figure 2 and Figure 3 The data source expected bucket shown is searched for the word to be associated. If the search is successful, an expected word combination containing the word to be associated is obtained. The expected word combination includes at least one expected word associated with the word to be associated. The input method association device also needs to extract the expected score of the association pair in the expected bucket.

[0098] Step S14: obtaining a second expected word combination of the to-be-associated word in the second expected bucket and a second expected score of each expected word.

[0099] In the embodiment of the present application, the input method association device is in the second expected bucket, such as Figure 4 and Figure 5 The data source expected bucket shown is searched for the word to be associated. If the search is successful, an expected word combination containing the word to be associated is obtained. The expected word combination includes at least one expected word associated with the word to be associated. The input method association device also needs to extract the expected score of the association pair in the expected bucket.

[0100] Step S15: merge the first expected word combination and the second expected word combination to generate a third expected word combination, and the third expected score of the expected word in the third expected word combination is weighted by merging the first expected score of the first expected bucket and the second expected score of the second expected bucket.

[0101] In the embodiment of the present application, the input method association device merges the first expected word combination extracted in step S13 and the second expected word combination extracted in step S14 to generate a third expected word combination, which can be regarded as a merged expected bucket.

[0102] Correspondingly, in the merged expected bucket, the expected scores of each expected word also need to be fused and calculated based on the expected scores of the expected words in the original expected buckets. Specifically, the input method association device records the length of the data source expected bucket as Ld, the length of the version expected bucket as Lv, the expected score of a single expectation in the data source expected bucket as Sd, and the expected score in the version expected bucket as Sv. In summary, the calculation method of the merged association score of a single expectation can be:

[0103] N=Sd*(Ld / (Ld+Lv)+Sv*(Lv / (Ld+Lv))

[0104] Thus, the input method association device calculates the expected scores of each combined expected word according to the total expected score sumN of all expectations and the association scores of each combined expected word:

[0105] S = N / sumN

[0106] For details, please refer to Figure 6 , Figure 6 , which is a data schematic diagram of an embodiment of the combined expected bucket provided by this application. As Figure 6 shown, the input method association device obtains multiple combined expected words of the input word "not believe", their combined association scores and combined expected scores according to the construction method shown in step S15. All this part of data is stored in the combined expected bucket, which is convenient for subsequent input method association output and input method association scoring, etc.

[0107] Step S16: Perform input method association output on the third expected word combination according to the third expected score.

[0108] In the embodiment of this application, the input method association device sorts the combined expected words according to the combined expected scores calculated in step S15, and outputs them in descending order of the combined expected scores for the user to select and use.

[0109] Furthermore, the input method association device can also score the generation use cases of the combined expected bucket. Specifically, the input method association device can normalize the expected scores calculated above before scoring, and then, according to the version expected bucket, find the corresponding expected scores of the first n expected words of each version's result in the combined expected bucket, and the sum of their scores is S1. The input method association device takes the sum of the first n combined expected scores of the combined expected bucket as S2, and calculates the effect of this generation use case through the following formula:

[0110] S = S1 / S2

[0111] For details, please refer to Figure 7 , Figure 7 , which is a data schematic diagram of an embodiment of the test result of the combined expected bucket provided by this application. As Figure 7 shown, through the above calculation process, the input method association device obtains the similarity between the expected results of each version in the version expected bucket and the expected results of the combined expected bucket, that is, the larger the S value, the higher the similarity. Thus, the accuracy of the generation use cases of the combined expected bucket can be analyzed.

[0112] In an embodiment of the present application, an input method association device obtains a first expected bucket and a second expected bucket, wherein the first expected bucket and the second expected bucket are constructed from different data dimensions respectively; inputs a word to be associated; obtains a first expected word combination of the word to be associated in the first expected bucket and a first expected score of each expected word; obtains a second expected word combination of the word to be associated in the second expected bucket and a second expected score of each expected word; merges the first expected word combination with the second expected word combination to generate a third expected word combination, wherein the third expected score of the expected word in the third expected word combination is weighted by fusion of the first expected score in the first expected bucket and the second expected score in the second expected bucket; outputs the third expected word combination through input method association according to the third expected score. Through the above-mentioned input method association method, multiple expectations of different data dimensions are used to achieve the accuracy of input method association, thereby improving the user experience.

[0113] As shown in the above embodiment, the user can refer to a large number of users who use the input method. In this case, the expected buckets constructed and used are general expected buckets; the user can also refer to the target users who use the input method. In this case, the expected buckets constructed and used are personalized expected buckets.

[0114] When using the general expected bucket, users can also add their own input method records to fine-tune the general expected bucket, thereby achieving personalized adjustments based on the general expected bucket. Figure 8 , Figure 8 It is a flowchart of another embodiment of the input method association method provided by the present application.

[0115] like Figure 8 As shown, the specific steps are as follows:

[0116] Step S41: Acquire historical association data of the user who inputs the word to be associated.

[0117] Step S42: Acquire the historical association score of the third expected word combination from the historical association data.

[0118] In an embodiment of the present application, the input method association device constructs a personalized data source expectation bucket and a version expectation bucket by utilizing the historical association data of the target user, and then merges them to obtain a merged expectation bucket, and extracts the historical association score of the expected word analyzed from the general expectation bucket from the merged expectation bucket.

[0119] It should be noted that the third expected score here is obtained by analyzing and calculating the data of the general expected bucket, while the historical association score is obtained by analyzing and calculating the data of the personalized expected bucket. The analysis and calculation parts have been explained in the above embodiments and will not be repeated here.

[0120] Step S43: updating the third expected score based on the historical association score.

[0121] In the embodiment of the present application, the input method association device weights and fuses the third expected score and the historical association score to obtain the final expected score. It should be noted that in the scenario emphasizing personalized performance, the input method association device can increase the weight of the historical association score and reduce the weight of the third expected score; in the scenario emphasizing general performance, the input method association device can reduce the weight of the historical association score and increase the weight of the third expected score.

[0122] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0123] In order to implement the above-mentioned input method association method, this application also proposes an input method association device, please refer to Fig. 9 , Fig. 9 It is a structural diagram of an embodiment of an input method association device provided by the present application.

[0124] The input method association device 500 of this embodiment includes a processor 51 , a memory 52 , an input / output device 53 , and a bus 54 .

[0125] The processor 51, memory 52, and input / output device 53 are connected to a bus 54 respectively. The memory 52 stores program data, and the processor 51 is used to execute the program data to implement the input method association method described in the above embodiment.

[0126] In the embodiment of the present application, the processor 51 may also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip having the ability to process signals. The processor 51 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 51 may also be any conventional processor, etc.

[0127] This application also provides a computer storage medium, please continue to refer to Fig.10 , Fig.10It is a structural diagram of an embodiment of a computer storage medium provided in the present application. The computer storage medium 600 stores a computer program 61. When the computer program 61 is executed by a processor, it is used to implement the input method association method of the above embodiment.

[0128] When the embodiments of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0129] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. An input method association method, characterized in that: The input method association method comprises: Obtaining a first expected bucket and a second expected bucket, wherein the first expected bucket and the second expected bucket are constructed from different data dimensions respectively; Input the word to be associated; Obtaining a first expected word combination of the to-be-associated word in the first expected bucket and a first expected score of each expected word thereof; Obtain a second expected word combination of the to-be-associated word in the second expected bucket and a second expected score of each expected word thereof; The first expected word combination and the second expected word combination are combined to generate a third expected word combination, wherein a third expected score of the expected word in the third expected word combination is weightedly fused by the first expected score of the first expected bucket and the second expected score of the second expected bucket; The third expected word combination is output through input method association according to the third expected score.

2. The input method association method according to claim 1, characterized in that: The first expected bucket is an expected bucket of data source; The input method association method further includes: Get the data source association collection; Based on the data source association set, a plurality of data source association input words and data source association expected combinations are segmented; Based on the number of occurrences of a combination of the same data source associative input words, obtaining data source association scores expected for all data source associations associated with the data source associative input words; The data source expected word of the data source associated input word is screened out based on the data source association scores expected by all data source associations, and the data source expected score of the data source expected word is obtained.

3. The input method association method according to claim 2, characterized in that: The step of screening out the data source expected word of the data source associated input word based on the data source associated expected scores of all data sources, and obtaining the data source expected score of the data source expected word includes: Sort all data source association expectations from high to low based on their data source association scores; Acquire a preset number of data source associative input words sorted from high to low as the data source expected words; Get the total score of data source association scores of all data source association input words; The data source expected score of each data source expected word is determined based on the ratio of the data source association score of each data source expected word to the total score.

4. The input method association method according to claim 1, characterized in that: The second expected bucket is a version expected bucket; The input method association method further includes: Get the version association combination of each input method version; Segmenting a plurality of combinations of version association input words and version association expectations based on the version association combination; Based on the expected number of versions associated with each version association input word and the expected positions of the associated versions, obtain the expected version association scores of all the associated versions; Based on the version association scores of all version association expectations, the version expected words of the version association input words are screened out, and the version expected scores of the version expected words are obtained.

5. The input method association method according to claim 4, characterized in that: The method of obtaining the expected version association scores of all associated version associations based on the number of associated version associations and the position of the associated version associations of each version association input word includes: Based on the expected version position of each version association and the number of compared versions, obtain the version position score of each version position; According to all version position scores and the number of appearing versions, the version association score expected for each version association is obtained.

6. The input method association method according to claim 1, characterized in that: The first expected bucket and the second expected bucket are expected buckets constructed for all user data.

7. The input method association method according to claim 6, characterized in that: After merging the first expected word combination and the second expected word combination to generate a third expected word combination, the input method association method further includes: Obtain historical association data of the user who inputs the word to be associated; Acquire a historical association score of the third expected word combination from the historical association data; The third expected score is updated based on the historical association score.

8. The input method association method according to claim 1, characterized in that: The first expected bucket and the second expected bucket are expected buckets constructed for separate user data.

9. An input method association device, characterized in that: The input method association device includes a memory and a processor coupled to the memory; The memory is used to store program data, and the processor is used to execute the program data to implement the input method association method as described in any one of claims 1 to 8.

10. A computer storage medium, characterized in that: The computer storage medium is used to store program data, and when the program data is executed by a computer, it is used to implement the input method association method according to any one of claims 1 to 8.

Images